© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12730
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions or payments

    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
    85
    +0.14
    0.6%
    223
    +0.11
    0.5%
    383
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.14
    0.08
    154
    +0.11
    0.11
    68
    +0.11
    0.04
    Negative Logits
    itals
    -0.89
    furt
    -0.72
     //[
    -0.71
     Correspond
    -0.70
    ITY
    -0.70
    aple
    -0.69
    ital
    -0.65
    zsche
    -0.65
    ilater
    -0.64
    xual
    -0.64
    POSITIVE LOGITS
     toll
    1.03
     booths
    0.97
     booth
    0.89
    s
    0.84
     Toll
    0.83
    atures
    0.83
    son
    0.81
    gate
    0.79
     plaza
    0.79
    sie
    0.79
    Activations Density 8.577%

    No Known Activations