© 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. 18930
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month followed by day

    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
    430
    +0.13
    0.6%
    707
    +0.11
    0.5%
    36
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    707
    +0.13
    0.05
    158
    +0.11
    0.05
    430
    +0.10
    0.05
    Negative Logits
     suite
    -0.69
    pan
    -0.66
     proximity
    -0.66
     basket
    -0.60
    ffen
    -0.60
     theaters
    -0.59
    nces
    -0.57
     grop
    -0.56
    anamo
    -0.55
     pan
    -0.55
    POSITIVE LOGITS
    eteenth
    1.20
     29
    0.99
     occasions
    0.96
     occasion
    0.95
     31
    0.94
     28
    0.94
    EMBER
    0.93
     26
    0.92
     27
    0.92
    imeo
    0.92
    Activations Density 0.062%

    No Known Activations