© 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 1536
    9. 8-RES_FS1536-JB
    11. 26
    Prev
    Next
    INDEX
    Explanations

    medical conditions and related terminology, specifically heart-related

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    235
    +0.12
    0.5%
    502
    +0.12
    0.5%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.13
    502
    +0.12
    0.09
    232
    +0.11
    0.09
    Negative Logits
    lain
    -1.04
    theless
    -0.79
    rooms
    -0.77
    */(
    -0.74
    ridges
    -0.70
    spin
    -0.70
    mort
    -0.70
    laus
    -0.67
    rified
    -0.66
    shire
    -0.65
    POSITIVE LOGITS
    Äĩ
    1.45
    plom
    1.17
    ère
    1.09
    orno
    1.02
    yah
    1.01
    qa
    1.01
    ya
    1.01
    Å¡
    0.99
    Äį
    0.99
    ablo
    0.97
    Activations Density 1.813%

    No Known Activations