© 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 24576
    9. 8-RES_FS24576-JB
    11. 9321
    Prev
    Next
    INDEX
    Explanations

    items listed in a list

    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
    497
    +0.12
    0.6%
    681
    +0.12
    0.5%
    222
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    558
    +0.12
    0.03
    222
    +0.12
    0.02
    39
    +0.11
    0.03
    Negative Logits
     Aber
    -0.77
     Ratt
    -0.71
    wav
    -0.65
     differe
    -0.61
    irgin
    -0.61
     Ath
    -0.61
    Whe
    -0.61
     fou
    -0.60
    birth
    -0.60
     Huck
    -0.59
    POSITIVE LOGITS
    erv
    1.03
    lists
    0.91
    ening
    0.88
    eners
    0.76
    worthy
    0.74
    wana
    0.74
    cloth
    0.73
    abet
    0.73
    icles
    0.72
    erve
    0.72
    Activations Density 0.029%

    No Known Activations