© 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 Local
    9. 6-RES_SCL-AJT
    11. 3997
    Prev
    Next
    INDEX
    Explanations

    email addresses and names related to various individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    200
    +0.03
    0.5%
    277
    +0.03
    0.5%
    31
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.03
    0.11
    232
    +0.03
    0.09
    587
    +0.03
    0.12
    Negative Logits
    LI
    -0.20
     Glob
    -0.20
     Isa
    -0.20
     Pixie
    -0.20
    MW
    -0.19
     Jericho
    -0.19
     Kum
    -0.18
     Tend
    -0.18
     Vengeance
    -0.18
     Chim
    -0.18
    POSITIVE LOGITS
    esta
    0.34
    fman
    0.27
    afort
    0.27
    email
    0.25
    rolet
    0.24
    rador
    0.23
    kefeller
    0.23
    quist
    0.22
     Podesta
    0.22
    clinton
    0.22
    Activations Density 11.553%

    No Known Activations