© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37338
    Prev
    Next
    INDEX
    Explanations

    references to financial elements and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.19
    0.9%
    685
    +0.12
    0.5%
    595
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    685
    +0.19
    0.02
    461
    +0.12
    0.03
    595
    +0.11
    0.03
    Negative Logits
     NCT
    -0.72
    eatures
    -0.71
     Hutch
    -0.68
     Fresno
    -0.67
    SOURCE
    -0.63
    lishes
    -0.63
    unci
    -0.63
    LINE
    -0.63
    USS
    -0.61
     Hastings
    -0.61
    POSITIVE LOGITS
     deposited
    1.06
     coupons
    1.03
     donated
    1.03
     coins
    1.01
     valued
    1.00
     exchanged
    1.00
    ãĥĺ
    1.00
     confiscated
    0.97
     expire
    0.95
     awarded
    0.94
    Activations Density 0.296%

    No Known Activations