© 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 Local
    5. 6-RES_SCL-AJT
    6. 45978
    Prev
    Next
    INDEX
    Explanations

    patterns related to newsletter subscriptions and email engagements

    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
    447
    +0.07
    0.8%
    420
    +0.05
    0.5%
    459
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.07
    0.54
    64
    +0.05
    -0.32
    745
    +0.05
    -0.20
    Negative Logits
    igans
    -0.27
    tymology
    -0.27
    gap
    -0.26
    ellen
    -0.26
    amaz
    -0.25
    ikuman
    -0.25
    bara
    -0.25
    tains
    -0.25
     Beir
    -0.24
    Parameters
    -0.24
    POSITIVE LOGITS
    entimes
    0.27
    resh
    0.26
    pload
    0.26
    isSpecialOrderable
    0.25
     Membership
    0.24
    scribe
    0.24
     tickets
    0.24
     Event
    0.24
     Wine
    0.23
    CAST
    0.23
    Activations Density 19.360%

    No Known Activations