© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14639
    Prev
    Next
    INDEX
    Explanations

    mentions of laboratory-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words that are related to scientific research or the medical field, specifically focusing on the term "lab"

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    351
    +0.17
    0.5%
    575
    +0.17
    0.5%
    328
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.08
    575
    +0.17
    0.07
    46
    +0.16
    0.05
    Negative Logits
     Marketable
    -1.10
    theless
    -1.05
    atra
    -0.95
    BOOK
    -0.94
    ACTED
    -0.94
    cut
    -0.92
     Ceres
    -0.87
     Oaks
    -0.86
    faced
    -0.85
     Ack
    -0.84
    POSITIVE LOGITS
    rador
    2.08
    yrinth
    1.71
    elling
    1.67
    orer
    1.41
    rosse
    1.39
    orously
    1.36
    elled
    1.32
    eled
    1.32
    inct
    1.28
    orers
    1.27
    Activations Density 0.987%

    No Known Activations