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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 802
    Prev
    Next
    INDEX
    Explanations

    positive assessments or compliments about someone's job performance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    762
    +0.11
    0.5%
    412
    +0.10
    0.5%
    7
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.04
    531
    +0.10
    0.03
    247
    +0.10
    0.03
    Negative Logits
    Tang
    -0.78
    ities
    -0.66
    ater
    -0.65
    NetMessage
    -0.64
    ults
    -0.62
    iku
    -0.62
    fty
    -0.61
    idden
    -0.61
     fears
    -0.61
    eros
    -0.60
    POSITIVE LOGITS
     portraying
    1.02
     illustrating
    0.88
    manship
    0.87
     educating
    0.87
     protecting
    0.87
     combating
    0.87
     keeping
    0.85
     balancing
    0.84
     capturing
    0.83
     showcasing
    0.83
    Activations Density 0.164%

    No Known Activations