© 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 12288
    9. 8-RES_FS12288-JB
    11. 852
    Prev
    Next
    INDEX
    Explanations

    technical and programming terms

    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
    481
    +0.20
    0.9%
    258
    +0.14
    0.6%
    670
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.20
    0.10
    575
    +0.14
    0.10
    537
    +0.10
    0.08
    Negative Logits
    stown
    -0.72
    apego
    -0.66
    çīĪ
    -0.66
    CHAT
    -0.61
    aeus
    -0.61
    Balt
    -0.59
    Reloaded
    -0.59
     pione
    -0.58
    atever
    -0.58
    bush
    -0.57
    POSITIVE LOGITS
     alike
    1.19
    paces
    1.10
    hips
    1.07
     such
    0.96
    pace
    0.94
    chool
    0.93
    hip
    0.90
    mith
    0.86
    ets
    0.83
     (>
    0.83
    Activations Density 0.611%

    No Known Activations