© 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. 9907
    Prev
    Next
    INDEX
    Explanations

    words related to political commentary and criticism

    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
    288
    +0.13
    0.6%
    289
    +0.13
    0.6%
    59
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.13
    0.01
    701
    +0.13
    0.01
    288
    +0.10
    0.01
    Negative Logits
    PUT
    -0.83
    nings
    -0.75
    swick
    -0.69
     Schwarzenegger
    -0.64
    PDATE
    -0.62
     fitting
    -0.62
    LOAD
    -0.61
     Collider
    -0.60
    zag
    -0.60
    berman
    -0.59
    POSITIVE LOGITS
    obia
    1.24
    ysics
    1.22
    ysical
    1.19
    orically
    1.18
    obic
    1.05
    orical
    0.98
    ilic
    0.97
    azard
    0.97
    ract
    0.97
    rax
    0.96
    Activations Density 0.024%

    No Known Activations