Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10011
    Prev
    Next
    INDEX
    Explanations

    phrases related to observing or noticing things

    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
    759
    +0.11
    0.5%
    373
    +0.11
    0.5%
    169
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.11
    0.03
    125
    +0.11
    0.02
    654
    +0.10
    0.02
    Negative Logits
    TOP
    -0.80
    Lew
    -0.66
    soever
    -0.61
    apo
    -0.61
    theless
    -0.59
    BER
    -0.59
    Chel
    -0.58
    rio
    -0.58
    isma
    -0.57
    atar
    -0.57
    POSITIVE LOGITS
     favorably
    0.78
    river
    0.75
    scope
    0.74
     nostalg
    0.73
     afar
    0.73
     retrospect
    0.71
     Compass
    0.68
     horrified
    0.68
     hindsight
    0.67
    glass
    0.66
    Activations Density 0.134%

    No Known Activations