© 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. 4074
    Prev
    Next
    INDEX
    Explanations

    email-related text such as email addresses, verification requests, and account creation steps

    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
    68
    +0.14
    0.6%
    447
    +0.11
    0.5%
    206
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.14
    0.04
    159
    +0.11
    0.06
    466
    +0.10
    0.06
    Negative Logits
    utsche
    -0.75
    bite
    -0.65
    sych
    -0.63
     Panther
    -0.62
     Bears
    -0.61
     Rath
    -0.60
    tsky
    -0.60
    fml
    -0.60
    nz
    -0.60
     Telecom
    -0.59
    POSITIVE LOGITS
    prise
    1.03
    prising
    1.02
    prises
    0.97
    tainment
    0.94
    taining
    0.88
    tain
    0.84
    tained
    0.78
     captcha
    0.75
    Password
    0.74
    obar
    0.74
    Activations Density 5.853%

    No Known Activations