© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14187
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics, laws, and societal issues

    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
    123
    +0.17
    0.6%
    27
    +0.17
    0.6%
    716
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.17
    0.06
    123
    +0.17
    0.05
    716
    +0.15
    0.05
    Negative Logits
    ibaba
    -1.35
    uyomi
    -1.08
    eanor
    -1.07
    endas
    -1.02
    itars
    -0.98
    etsk
    -0.98
     separat
    -0.93
     Parenthood
    -0.92
    abis
    -0.92
     havoc
    -0.91
    POSITIVE LOGITS
    è¦ļéĨĴ
    0.92
     chronological
    0.91
     mile
    0.91
    umbers
    0.91
     Logged
    0.90
     margin
    0.89
    committee
    0.88
    Universal
    0.87
     landslide
    0.84
     margins
    0.83
    Activations Density 0.927%

    No Known Activations