© 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. 45742
    Prev
    Next
    INDEX
    Explanations

    mentions of subscriptions and payment methods in the text

    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
    +0.15
    0.8%
    726
    +0.12
    0.6%
    575
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.15
    0.14
    288
    +0.12
    0.19
    651
    +0.10
    0.09
    Negative Logits
    ochet
    -0.80
    inus
    -0.78
    esty
    -0.74
    est
    -0.74
    umi
    -0.73
    animous
    -0.72
    estation
    -0.71
    sein
    -0.71
    auga
    -0.70
    arnaev
    -0.70
    POSITIVE LOGITS
     fee
    0.74
     headache
    0.69
     binge
    0.68
     renewal
    0.67
     waivers
    0.66
     fare
    0.65
     fees
    0.64
     shopping
    0.62
    ħĭ
    0.62
     Clicker
    0.59
    Activations Density 7.645%

    No Known Activations