© 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 49152
    9. 8-RES_FS49152-JB
    11. 45840
    Prev
    Next
    INDEX
    Explanations

    words associated with addressing issues or concerns, particularly in a formal or supportive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.17
    0.8%
    101
    +0.13
    0.6%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.17
    0.03
    276
    +0.13
    0.03
    3
    +0.11
    0.02
    Negative Logits
    perty
    -0.72
     challeng
    -0.72
     territ
    -0.69
     disg
    -0.65
    dfx
    -0.61
    FIL
    -0.61
    printf
    -0.59
     withd
    -0.59
    erguson
    -0.56
     respectively
    -0.56
    POSITIVE LOGITS
    ments
    1.19
     Yourself
    1.15
    ations
    1.14
    ably
    1.09
    ables
    1.06
    able
    1.05
    ability
    1.03
    ment
    1.01
    ing
    1.01
    ings
    1.00
    Activations Density 0.066%

    No Known Activations