© 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. 45869
    Prev
    Next
    INDEX
    Explanations

    information related to business deals or negotiations

    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
    +0.31
    1.7%
    481
    +0.14
    0.8%
    596
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.31
    0.40
    270
    +0.14
    0.06
    375
    +0.08
    0.04
    Negative Logits
    ety
    -0.58
    ingly
    -0.58
    giene
    -0.57
    isec
    -0.52
    hest
    -0.52
     ERROR
    -0.52
    jah
    -0.52
    claimer
    -0.52
    Fact
    -0.50
     (âĪĴ
    -0.50
    POSITIVE LOGITS
     someday
    0.92
     relocate
    0.75
     mosqu
    0.72
     bid
    0.70
     bids
    0.69
     candidacy
    0.68
    soDeliveryDate
    0.67
     future
    0.65
     relocation
    0.61
     feasibility
    0.61
    Activations Density 30.574%

    No Known Activations