© 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 12288
    5. 8-RES_FS12288-JB
    6. 9579
    Prev
    Next
    INDEX
    Explanations

    the preposition "to" followed by a verb or a noun phrase that reflects responsibility or blame

    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
    314
    +0.14
    0.7%
    718
    +0.12
    0.5%
    373
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.14
    0.05
    608
    +0.12
    0.04
    49
    +0.12
    0.04
    Negative Logits
    Dur
    -0.67
     nets
    -0.64
     scares
    -0.62
    ById
    -0.62
     deductions
    -0.62
     reperto
    -0.61
     loopholes
    -0.61
     distortions
    -0.60
     ain
    -0.60
     fluctuations
    -0.59
    POSITIVE LOGITS
    asted
    1.38
    asting
    1.27
    wered
    1.14
    lled
    1.08
    asters
    1.07
    ying
    1.06
    pless
    1.06
    wing
    1.02
     blame
    1.02
    lling
    0.98
    Activations Density 0.165%

    No Known Activations