© 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 24576
    9. 8-RES_FS24576-JB
    11. 18919
    Prev
    Next
    INDEX
    Explanations

    mentions or uses of the word "in"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    745
    +0.14
    0.6%
    665
    +0.11
    0.5%
    22
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.14
    0.04
    123
    +0.11
    0.03
    665
    +0.10
    0.04
    Negative Logits
    76561
    -0.72
    ydia
    -0.66
    HAEL
    -0.65
    rio
    -0.63
    osal
    -0.63
    iable
    -0.63
    $
    -0.62
    ]}
    -0.60
    llah
    -0.60
     Niet
    -0.58
    POSITIVE LOGITS
     conjunction
    1.55
     lieu
    1.36
     tandem
    1.07
     vain
    0.97
     emergencies
    0.97
    ordinate
    0.96
     situ
    0.95
     vitro
    0.93
     accordance
    0.92
     constructing
    0.90
    Activations Density 0.146%

    No Known Activations