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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 22247
    Prev
    Next
    INDEX
    Explanations

    mentions of TV channels, particularly focusing on Channel 8 and other related channels

    oai_token-act-pair · gpt-4o-miniTriggered 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
    288
    +0.14
    0.6%
    289
    +0.13
    0.6%
    271
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.14
    0.01
    455
    +0.13
    0.02
    271
    +0.12
    0.02
    Negative Logits
    enhagen
    -0.75
    hiro
    -0.67
     Raiders
    -0.66
    dden
    -0.66
    berman
    -0.63
    ggies
    -0.62
     Gat
    -0.60
     Gloria
    -0.59
    stad
    -0.59
    docker
    -0.59
    POSITIVE LOGITS
     channels
    0.88
     channel
    0.88
    Channel
    0.82
    washer
    0.75
    agall
    0.74
    ting
    0.74
    channel
    0.74
    Fire
    0.73
    annels
    0.71
     blockers
    0.71
    Activations Density 0.017%

    No Known Activations