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

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 10625
    Prev
    Next
    INDEX
    Explanations

    geographical locations or points of interest

    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
    +0.12
    0.6%
    496
    +0.11
    0.5%
    537
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.02
    496
    +0.11
    0.02
    288
    +0.09
    0.02
    Negative Logits
    uting
    -0.81
    istically
    -0.78
    gain
    -0.78
    */(
    -0.76
    acl
    -0.75
    aciously
    -0.73
    ificial
    -0.70
    BuyableInstoreAndOnline
    -0.70
    iasis
    -0.70
    jury
    -0.70
    POSITIVE LOGITS
     Passage
    1.09
     Corridor
    1.08
     Territories
    1.00
     Airlines
    0.95
     Asia
    0.93
     Regional
    0.92
     Asians
    0.86
     Asian
    0.85
     Region
    0.81
     Arkansas
    0.81
    Activations Density 0.028%

    No Known Activations