© 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
    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. 5676
    Prev
    Next
    INDEX
    Explanations

    phrases related to walls

    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
    288
    +0.22
    0.7%
    491
    +0.17
    0.6%
    326
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.22
    0.05
    288
    +0.17
    0.06
    99
    +0.15
    0.04
    Negative Logits
    Gene
    -1.18
    lihood
    -1.05
    ensation
    -0.99
    amate
    -0.98
    CENT
    -0.97
    Wild
    -0.94
    ptive
    -0.94
    ria
    -0.93
    ECH
    -0.92
    arin
    -0.91
    POSITIVE LOGITS
    papers
    1.72
    abies
    1.48
     thickness
    1.30
    paper
    1.29
     walls
    1.29
    aby
    1.27
    clock
    1.19
     wall
    1.16
     separating
    1.14
    buster
    1.13
    Activations Density 0.614%

    No Known Activations