Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13861
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to educational institutions

    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
    285
    +0.16
    0.6%
    723
    +0.16
    0.5%
    99
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.06
    555
    +0.16
    0.04
    441
    +0.14
    0.03
    Negative Logits
     GOODMAN
    -1.13
    DragonMagazine
    -1.08
    manship
    -0.98
    STER
    -0.91
     DRAGON
    -0.85
     Respond
    -0.84
     Hunters
    -0.84
     Signed
    -0.84
     buckle
    -0.84
    Reviewer
    -0.83
    POSITIVE LOGITS
    ighton
    1.46
    aky
    1.25
    aking
    1.24
    ase
    1.24
    atio
    1.19
    eping
    1.18
    ruption
    1.15
    enery
    1.15
    vice
    1.12
    ername
    1.11
    Activations Density 0.810%

    No Known Activations