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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13043
    Prev
    Next
    INDEX
    Explanations

    names of software programs and technical terms related to programming

    oai_token-act-pair · gpt-3.5-turbo
    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
    653
    +0.14
    0.5%
    101
    +0.13
    0.5%
    114
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.14
    0.05
    653
    +0.13
    0.05
    114
    +0.13
    0.05
    Negative Logits
    psey
    -1.28
    yrinth
    -1.25
    elaide
    -1.21
    ilib
    -1.08
    irth
    -1.08
    isoft
    -1.02
    romy
    -1.01
    oulos
    -0.97
    ipolar
    -0.97
    icult
    -0.97
    POSITIVE LOGITS
    plates
    1.84
    paces
    1.72
    plate
    1.58
    names
    1.23
    ames
    1.18
    paced
    1.17
    brand
    1.17
    pace
    1.12
     aliases
    1.05
     names
    1.05
    Activations Density 0.894%

    No Known Activations