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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 37107
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "lecture" and related forms

    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
    651
    +0.12
    0.5%
    288
    +0.10
    0.5%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.12
    0.00
    11
    +0.10
    0.01
    235
    +0.10
    0.01
    Negative Logits
    PDATE
    -0.67
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    FUL
    -0.65
    KNOWN
    -0.64
     holiest
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
     Leopard
    -0.62
     interfering
    -0.62
    theless
    -0.62
    ledged
    -0.62
    POSITIVE LOGITS
    ures
    1.51
    urers
    1.30
    ure
    1.27
    ured
    1.23
    uring
    1.16
    urer
    1.15
    ories
    1.14
    orial
    1.11
    itle
    1.11
    atures
    1.06
    Activations Density 0.005%

    No Known Activations