© 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 EvalsExportsinterp-engineNEWAPI 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. 2737
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets related to manipulating URL paths and domains using JavaScript and programming techniques

    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
    522
    +0.11
    0.5%
    323
    +0.11
    0.5%
    141
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    0.02
    326
    +0.11
    0.03
    284
    +0.10
    0.03
    Negative Logits
     mechanically
    -0.82
     leaps
    -0.78
     disarm
    -0.78
     gearing
    -0.77
     dispel
    -0.76
     induct
    -0.76
     reactions
    -0.75
     paralysis
    -0.73
     reversible
    -0.72
     disband
    -0.70
    POSITIVE LOGITS
    localhost
    1.46
    example
    1.44
    username
    1.40
    foo
    1.38
    USER
    1.35
    XXXX
    1.20
    password
    1.19
    domain
    1.17
    xxxx
    1.13
    NAME
    1.07
    Activations Density 0.110%

    No Known Activations