© 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 24576
    9. 8-RES_FS24576-JB
    11. 2111
    Prev
    Next
    INDEX
    Explanations

    locations or place names

    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
    624
    +0.12
    0.6%
    527
    +0.11
    0.5%
    376
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    624
    +0.12
    0.03
    65
    +0.11
    0.03
    376
    +0.10
    0.03
    Negative Logits
    etsk
    -0.99
    cffff
    -0.89
     confir
    -0.79
    displayText
    -0.79
    Downloadha
    -0.79
    staking
    -0.78
    ptive
    -0.74
     reluct
    -0.71
    undo
    -0.68
    aminer
    -0.68
    POSITIVE LOGITS
    minster
    1.20
     Indies
    1.19
    cott
    1.17
     Coast
    1.17
    chester
    1.11
    lake
    1.09
    side
    1.08
    fall
    1.07
    phal
    1.05
     Midlands
    1.05
    Activations Density 0.026%

    No Known Activations