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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13820
    Prev
    Next
    INDEX
    Explanations

    financial and market-related terms, such as market capitalization, market share, and company valuation

    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
    573
    +0.12
    0.4%
    39
    +0.11
    0.4%
    442
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.12
    0.04
    288
    +0.11
    0.05
    323
    +0.10
    0.03
    Negative Logits
     clot
    -0.81
    beck
    -0.79
    iday
    -0.77
    otropic
    -0.77
    usc
    -0.76
    imar
    -0.75
    buf
    -0.74
     hunger
    -0.74
    jon
    -0.73
     Zan
    -0.72
    POSITIVE LOGITS
    jri
    0.97
    ributed
    0.88
    olo
    0.86
    eers
    0.81
    perse
    0.80
    =~
    0.79
    ENCE
    0.78
    workshop
    0.78
    imate
    0.77
    lay
    0.77
    Activations Density 0.212%

    No Known Activations