© 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 EvalsExportsinterp-engineNEWAPI 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. 2083
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and statistics

    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
    +0.17
    0.7%
    387
    +0.14
    0.5%
    44
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.23
    67
    +0.14
    0.14
    481
    +0.10
    0.18
    Negative Logits
    etsk
    -1.01
    undai
    -0.89
    arnaev
    -0.86
    vati
    -0.83
    ersen
    -0.83
    wagen
    -0.81
    hement
    -0.80
    pherd
    -0.80
    eatures
    -0.80
    anwhile
    -0.79
    POSITIVE LOGITS
    activity
    0.79
     proportions
    0.77
    thood
    0.76
    votes
    0.72
    ravity
    0.72
    stuff
    0.70
     versus
    0.70
     liberalism
    0.69
     capitalism
    0.69
    âī
    0.64
    Activations Density 4.663%

    No Known Activations