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. 413
    Prev
    Next
    INDEX
    Explanations

    phrases related to logical reasoning

    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
    •Layer 6 UMAP region: Mixed in middle - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.17
    0.6%
    655
    +0.17
    0.6%
    672
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.09
    613
    +0.17
    0.06
    641
    +0.16
    0.06
    Negative Logits
    lain
    -0.96
    oli
    -0.93
    hold
    -0.92
    orks
    -0.89
    adal
    -0.86
     Volunte
    -0.86
    aper
    -0.86
    ding
    -0.84
     national
    -0.84
    avez
    -0.84
    POSITIVE LOGITS
    ophical
    1.27
    istically
    1.21
    istical
    1.21
     posit
    1.20
    ophe
    1.11
    \\\\\\\\
    1.08
    ical
    1.08
    cean
    1.08
     underpin
    1.06
    arily
    1.06
    Activations Density 0.970%

    No Known Activations