© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41539
    Prev
    Next
    INDEX
    Explanations

    keywords related to programs, policies, and structured classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    344
    +0.08
    0.3%
    306
    +0.07
    0.3%
    468
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.08
    0.01
    659
    +0.07
    0.01
    227
    +0.06
    0.00
    Negative Logits
    apons
    -0.82
    creation
    -0.76
    pter
    -0.73
    Priv
    -0.71
    Gh
    -0.70
    emark
    -0.68
    arnaev
    -0.66
    tein
    -0.65
    mins
    -0.65
     resultant
    -0.64
    POSITIVE LOGITS
     Kinnikuman
    0.75
     Gallagher
    0.65
    AMI
    0.64
     lou
    0.64
     Amph
    0.63
     rehe
    0.62
    ARE
    0.62
    ares
    0.61
     defer
    0.61
    .''
    0.60
    Activations Density 0.021%

    No Known Activations