© 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. 39991
    Prev
    Next
    INDEX
    Explanations

    verifications and prompts related to email subscriptions

    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
    208
    +0.08
    0.6%
    311
    +0.08
    0.5%
    631
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.08
    0.05
    311
    +0.08
    -0.03
    43
    +0.07
    0.05
    Negative Logits
    NetMessage
    -0.52
     Sparrow
    -0.51
    hill
    -0.48
    knife
    -0.48
    RESULTS
    -0.46
    zhen
    -0.45
    MpServer
    -0.45
    lot
    -0.45
    istance
    -0.45
    EStreamFrame
    -0.45
    POSITIVE LOGITS
     Javascript
    0.50
     verify
    0.45
    irmation
    0.44
     email
    0.43
     YOUR
    0.42
    icio
    0.42
    iquette
    0.41
     Gmail
    0.41
     Rodham
    0.41
    Java
    0.40
    Activations Density 4.642%

    No Known Activations