© 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. 13680
    Prev
    Next
    INDEX
    Explanations

    descriptions of narratives involving battling opponents and overcoming challenges in a game or story

    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
    181
    +0.11
    0.5%
    585
    +0.09
    0.4%
    442
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.06
    181
    +0.09
    0.04
    737
    +0.09
    0.03
    Negative Logits
    NPR
    -0.80
    Percent
    -0.75
    CVE
    -0.71
    PDATE
    -0.71
    Owner
    -0.70
    ITNESS
    -0.68
    POSE
    -0.66
    ThumbnailImage
    -0.64
    @#&
    -0.64
    PN
    -0.63
    POSITIVE LOGITS
     maze
    1.11
     corridors
    1.08
     veins
    1.01
     boundaries
    0.93
     labyrinth
    0.93
     loops
    0.92
     channels
    0.91
     aisle
    0.91
     hoops
    0.91
     tunnels
    0.89
    Activations Density 0.325%

    No Known Activations