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 49152
    5. 8-RES_FS49152-JB
    6. 45745
    Prev
    Next
    INDEX
    Explanations

    identifiers related to specific events or individuals, particularly in the context of news and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    726
    +0.10
    0.5%
    558
    +0.10
    0.5%
    756
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.03
    659
    +0.10
    0.03
    284
    +0.10
    0.03
    Negative Logits
    soDeliveryDate
    -0.87
    wcs
    -0.70
    ĸļ
    -0.69
     rapists
    -0.64
    externalActionCode
    -0.64
     blocks
    -0.64
     disadvant
    -0.63
    cheat
    -0.62
    CHR
    -0.62
     phon
    -0.61
    POSITIVE LOGITS
    acci
    1.15
    tein
    0.92
    ruary
    0.89
    bender
    0.84
    heit
    0.81
    uala
    0.79
    stein
    0.79
    ima
    0.78
    iman
    0.73
    wald
    0.72
    Activations Density 0.102%

    No Known Activations