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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 37271
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and manufacturing details

    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
    373
    +0.14
    0.6%
    314
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.14
    0.02
    314
    +0.11
    -0.00
    326
    +0.10
    0.03
    Negative Logits
    tsky
    -0.70
    igslist
    -0.68
    byn
    -0.66
    omething
    -0.64
    soDeliveryDate
    -0.61
    dfx
    -0.61
    )."
    -0.61
    iatrics
    -0.60
    theless
    -0.60
    ocobo
    -0.60
    POSITIVE LOGITS
     Description
    0.84
     Name
    0.77
     Category
    0.73
    ²¾
    0.73
     Gender
    0.72
     Detected
    0.67
     Tags
    0.64
    verages
    0.62
     Title
    0.62
     Sheet
    0.62
    Activations Density 0.097%

    No Known Activations