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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 5259
    Prev
    Next
    INDEX
    Explanations

    roundups of news stories

    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
    508
    +0.12
    0.5%
    108
    +0.12
    0.5%
    350
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.12
    0.04
    194
    +0.12
    0.03
    508
    +0.11
    0.03
    Negative Logits
    İĭ
    -0.80
     Shank
    -0.79
    stairs
    -0.78
     Borders
    -0.72
    lease
    -0.72
     Peel
    -0.71
    olor
    -0.71
    zik
    -0.71
     Boo
    -0.70
    croft
    -0.70
    POSITIVE LOGITS
    Science
    0.95
    agascar
    0.91
     roundup
    0.84
    scill
    0.78
    NEWS
    0.76
    restling
    0.75
    âĹ
    0.74
    Health
    0.74
     Vacc
    0.73
    Side
    0.73
    Activations Density 0.200%

    No Known Activations