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. 5211
    Prev
    Next
    INDEX
    Explanations

    names of locations or historical events, especially related to war or politics

    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
    558
    +0.12
    0.5%
    705
    +0.11
    0.4%
    476
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.12
    0.03
    373
    +0.11
    -0.01
    659
    +0.11
    0.03
    Negative Logits
     transpl
    -0.80
     interpol
    -0.80
     cod
    -0.79
     dart
    -0.79
     mot
    -0.73
     partName
    -0.72
     Phant
    -0.72
     simul
    -0.72
     jug
    -0.71
    phony
    -0.71
    POSITIVE LOGITS
    orage
    1.10
    atown
    1.06
    andise
    1.05
    amac
    1.01
    ione
    0.93
    ablishment
    0.92
    inese
    0.92
     Cassidy
    0.91
    anwhile
    0.90
    atchewan
    0.88
    Activations Density 0.072%

    No Known Activations