© 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. 18886
    Prev
    Next
    INDEX
    Explanations

    topics related to policy and societal issues

    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
    481
    +0.12
    0.6%
    679
    +0.12
    0.5%
    724
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.12
    0.08
    225
    +0.12
    0.07
    575
    +0.10
    0.07
    Negative Logits
    Õ
    -0.84
    thumbnails
    -0.81
    Vel
    -0.74
    ãĤ¨ãĥ«
    -0.74
    INAL
    -0.71
    APTER
    -0.70
    SN
    -0.70
    yss
    -0.67
    OV
    -0.66
    RIC
    -0.65
    POSITIVE LOGITS
    afe
    1.00
    pace
    0.92
    paces
    0.89
    hops
    0.86
    chool
    0.84
     arising
    0.84
     pertaining
    0.84
    afety
    0.83
     abound
    0.83
    heet
    0.83
    Activations Density 0.318%

    No Known Activations