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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12932
    Prev
    Next
    INDEX
    Explanations

    phrases related to repetition or frequency

    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
    71
    +0.13
    0.6%
    99
    +0.12
    0.5%
    261
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.13
    0.02
    71
    +0.12
    0.02
    261
    +0.10
    0.02
    Negative Logits
    toc
    -0.82
    Reviewer
    -0.80
    ocard
    -0.71
    ghai
    -0.70
    early
    -0.69
    Soc
    -0.68
    igans
    -0.68
    soc
    -0.67
    ocene
    -0.67
    LCS
    -0.66
    POSITIVE LOGITS
    theless
    0.94
     reiter
    0.92
     reiterated
    0.88
     reaff
    0.88
     contradicted
    0.87
     unsuccessful
    0.87
     voiced
    0.85
     interrupted
    0.84
     debunked
    0.84
     repeated
    0.83
    Activations Density 0.042%

    No Known Activations