© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10124
    Prev
    Next
    INDEX
    Explanations

    details about events, accomplishments, and qualities of individuals or groups

    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
    373
    +0.13
    0.6%
    756
    +0.11
    0.5%
    544
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.13
    0.09
    43
    +0.11
    0.07
    418
    +0.10
    0.07
    Negative Logits
    ivity
    -0.61
    itol
    -0.59
    minent
    -0.58
    ls
    -0.57
    gow
    -0.56
    itation
    -0.56
    iple
    -0.56
    oba
    -0.55
    conom
    -0.54
    chnology
    -0.54
    POSITIVE LOGITS
     respectively
    1.47
     whichever
    1.00
     depending
    0.93
    depending
    0.93
     albeit
    0.92
     according
    0.81
     etc
    0.81
     including
    0.79
     although
    0.78
     accordingly
    0.76
    Activations Density 0.543%

    No Known Activations