Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4263
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions and business ownership

    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
    +0.22
    1.0%
    587
    +0.12
    0.5%
    481
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.22
    0.21
    393
    +0.12
    0.35
    608
    +0.12
    0.26
    Negative Logits
    urai
    -0.76
    escription
    -0.74
    pressure
    -0.73
    opsy
    -0.72
    enegger
    -0.68
    paio
    -0.67
    autions
    -0.66
    nah
    -0.65
    ague
    -0.65
    ogene
    -0.65
    POSITIVE LOGITS
     lucrative
    0.96
     property
    0.87
    ilts
    0.81
     goods
    0.81
     groceries
    0.81
     merchandise
    0.79
     coveted
    0.78
     bitcoins
    0.77
     tickets
    0.75
     Property
    0.75
    Activations Density 17.507%

    No Known Activations