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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11163
    Prev
    Next
    INDEX
    Explanations

    names of people and places intertwined with activities or specific events

    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
    481
    +0.20
    0.9%
    503
    +0.11
    0.5%
    420
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.20
    0.04
    224
    +0.11
    0.05
    14
    +0.11
    0.03
    Negative Logits
    trop
    -0.78
    osphere
    -0.78
    abase
    -0.74
    vironment
    -0.72
    grain
    -0.72
    availability
    -0.72
    orgetown
    -0.71
    verage
    -0.71
    fecture
    -0.70
    iti
    -0.70
    POSITIVE LOGITS
     brothers
    1.16
     siblings
    1.07
     selves
    1.02
     duo
    1.01
     reunited
    1.00
     twins
    1.00
     sisters
    0.99
     husbands
    0.96
     cousins
    0.96
     sons
    0.91
    Activations Density 0.401%

    No Known Activations