© 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 24576
    9. 8-RES_FS24576-JB
    11. 7160
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    471
    +0.11
    0.5%
    74
    +0.10
    0.4%
    270
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.11
    0.02
    74
    +0.10
    0.02
    647
    +0.09
    0.01
    Negative Logits
    leneck
    -0.74
    Reviewer
    -0.73
    irs
    -0.73
    sers
    -0.72
    ales
    -0.71
    ifferent
    -0.71
    onsense
    -0.70
    ictive
    -0.69
    phabet
    -0.67
    alls
    -0.67
    POSITIVE LOGITS
     possible
    0.93
     practicable
    0.86
     Possible
    0.80
     December
    0.77
     1955
    0.76
     September
    0.74
     February
    0.74
     January
    0.74
     June
    0.73
     October
    0.72
    Activations Density 0.030%

    No Known Activations