© 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. 8127
    Prev
    Next
    INDEX
    Explanations

    text related to different "Generations" or blocks of content within longer texts

    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
    642
    +0.11
    0.6%
    275
    +0.10
    0.5%
    220
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    232
    +0.10
    0.03
    525
    +0.08
    0.03
    Negative Logits
    kefeller
    -0.75
    thin
    -0.69
    psey
    -0.69
    lihood
    -0.66
     prosec
    -0.65
    borg
    -0.64
    acea
    -0.62
    ĺħ
    -0.62
     seiz
    -0.62
     nep
    -0.60
    POSITIVE LOGITS
     Lad
    0.61
    utral
    0.59
    vernment
    0.59
     Screw
    0.58
    LV
    0.58
    initions
    0.57
     Van
    0.56
    Vs
    0.55
     Trend
    0.55
     Gand
    0.55
    Activations Density 0.186%

    No Known Activations