© 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. 1486
    Prev
    Next
    INDEX
    Explanations

    words related to personal names, places, and organizations

    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
    420
    +0.15
    0.6%
    208
    +0.14
    0.6%
    683
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.09
    288
    +0.14
    0.10
    683
    +0.13
    0.07
    Negative Logits
    ¥ŀ
    -0.91
    ĺħ
    -0.82
     lapse
    -0.82
     tremend
    -0.76
    Downloadha
    -0.76
    BuyableInstoreAndOnline
    -0.74
    iasm
    -0.73
     princ
    -0.72
    uncture
    -0.70
    anwhile
    -0.69
    POSITIVE LOGITS
    iquette
    0.99
    lements
    0.96
    erer
    0.92
    rigan
    0.91
    eland
    0.89
    ucc
    0.89
    emo
    0.84
    itus
    0.83
    iny
    0.83
    erers
    0.83
    Activations Density 1.631%

    No Known Activations