© 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
    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. 14178
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic locations or infrastructural projects

    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
    114
    +0.06
    0.5%
    321
    +0.06
    0.5%
    298
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.06
    0.03
    373
    +0.06
    -0.01
    41
    +0.05
    0.02
    Negative Logits
    GOP
    -0.35
    nard
    -0.34
    ILY
    -0.34
    anza
    -0.34
    Xi
    -0.33
    anos
    -0.33
    Nev
    -0.32
     spirited
    -0.32
    araoh
    -0.32
    IAN
    -0.31
    POSITIVE LOGITS
    ĸļ
    0.45
    reet
    0.41
    itch
    0.39
     Catch
    0.38
     Ltd
    0.37
     Processing
    0.36
    ells
    0.34
    eps
    0.34
     Picture
    0.34
    hal
    0.34
    Activations Density 0.091%

    No Known Activations