© 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. 10179
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong opinion or evaluation

    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
    +0.12
    0.5%
    462
    +0.10
    0.5%
    350
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.03
    262
    +0.10
    0.02
    9
    +0.10
    0.03
    Negative Logits
    aido
    -0.81
    pload
    -0.80
    kees
    -0.76
    eport
    -0.75
    maid
    -0.69
    emis
    -0.69
    lain
    -0.69
    anwhile
    -0.69
    ibo
    -0.68
    ulet
    -0.68
    POSITIVE LOGITS
     collision
    0.74
     rejection
    0.74
     brawl
    0.74
    edly
    0.72
     insanity
    0.71
     collisions
    0.71
     racism
    0.70
     badass
    0.70
     hostility
    0.70
     refusal
    0.69
    Activations Density 0.186%

    No Known Activations