© 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. 14612
    Prev
    Next
    INDEX
    Explanations

    words related to vehicles, specifically focusing on tires

    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
    326
    +0.15
    0.6%
    288
    +0.14
    0.5%
    718
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.06
    288
    +0.14
    0.08
    289
    +0.11
    0.01
    Negative Logits
    rooms
    -1.00
     Wong
    -0.94
    ulton
    -0.89
    ardy
    -0.88
    vati
    -0.83
    foundland
    -0.83
    heter
    -0.83
    AMY
    -0.82
    arov
    -0.80
    VD
    -0.80
    POSITIVE LOGITS
    vable
    1.12
     sidew
    0.99
     tread
    0.94
     tires
    0.93
    pel
    0.93
     pedal
    0.91
    pit
    0.91
    hog
    0.86
     tyre
    0.86
     scree
    0.86
    Activations Density 0.598%

    No Known Activations