© 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 12288
    9. 8-RES_FS12288-JB
    11. 10602
    Prev
    Next
    INDEX
    Explanations

    phrases related to making demands or requests

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    321
    +0.10
    0.5%
    38
    +0.09
    0.4%
    300
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.10
    0.03
    52
    +0.09
    0.03
    184
    +0.08
    0.02
    Negative Logits
    ãĥĦ
    -0.89
    VERTISEMENT
    -0.73
    nown
    -0.73
    vironment
    -0.73
    Ń·
    -0.71
    este
    -0.70
    ãĥ³ãĤ¸
    -0.70
    beit
    -0.70
    mania
    -0.68
    abet
    -0.67
    POSITIVE LOGITS
     clarification
    0.90
     answers
    0.89
     retribution
    0.85
     obedience
    0.85
     payment
    0.84
     quotas
    0.83
     repayment
    0.83
     conformity
    0.82
     explanations
    0.82
     forgiveness
    0.79
    Activations Density 0.118%

    No Known Activations