© 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. 3646
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names or titles related to historical events, people, or places

    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
    603
    +0.08
    0.5%
    442
    +0.07
    0.4%
    683
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.08
    0.05
    398
    +0.07
    0.04
    232
    +0.07
    0.04
    Negative Logits
    ĸļ
    -0.57
     trad
    -0.55
    VERTISEMENT
    -0.53
     timeless
    -0.49
     continuous
    -0.49
     Tasmania
    -0.48
    dayName
    -0.48
     tracing
    -0.48
     tert
    -0.47
    externalActionCode
    -0.45
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.71
    burg
    0.63
     Brothers
    0.62
    achu
    0.61
    viks
    0.59
    azy
    0.58
    ichi
    0.56
    iev
    0.55
    icy
    0.54
    yg
    0.54
    Activations Density 0.324%

    No Known Activations