© 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. 45929
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Illinois

    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
    99
    +0.17
    0.8%
    235
    +0.10
    0.5%
    13
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.17
    0.13
    514
    +0.10
    0.11
    308
    +0.10
    0.11
    Negative Logits
    eful
    -0.94
    eting
    -0.92
    efully
    -0.88
    rous
    -0.84
    iling
    -0.81
    alore
    -0.80
    acks
    -0.79
    idth
    -0.76
    aces
    -0.75
    orie
    -0.75
    POSITIVE LOGITS
     Masonic
    0.79
    REDACTED
    0.78
     Illinois
    0.68
    ECD
    0.68
     reven
    0.67
     Bulldogs
    0.65
     sidx
    0.65
     hosp
    0.63
    Directory
    0.63
     TAMADRA
    0.62
    Activations Density 7.676%

    No Known Activations