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. 41409
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical data and its implications

    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
    447
    +0.60
    3.8%
    480
    +0.22
    1.4%
    464
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.60
    0.13
    480
    +0.22
    -0.02
    575
    +0.10
    0.09
    Negative Logits
    utterstock
    -0.50
    quartered
    -0.50
     Latest
    -0.44
    named
    -0.43
     reportedly
    -0.42
     Ezek
    -0.42
     Browse
    -0.42
     bolstered
    -0.42
    cerpt
    -0.41
     strikingly
    -0.40
    POSITIVE LOGITS
    )."
    0.68
    ?".
    0.64
    ..."
    0.58
     ..."
    0.56
    â̦"
    0.56
    !".
    0.55
    ··
    0.53
    .ãĢį
    0.51
    â̦."
    0.51
     â̦"
    0.50
    Activations Density 1.916%

    No Known Activations