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. 11233
    Prev
    Next
    INDEX
    Explanations

    verbs related to operation or functioning

    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
    566
    +0.14
    0.6%
    288
    +0.13
    0.6%
    497
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.02
    665
    +0.13
    0.02
    567
    +0.12
    0.02
    Negative Logits
    grave
    -0.79
    hus
    -0.74
    plet
    -0.73
    hon
    -0.72
    ilde
    -0.68
    urd
    -0.65
    username
    -0.65
    ildo
    -0.65
    alon
    -0.65
    ixed
    -0.65
    POSITIVE LOGITS
     independently
    0.91
     continuously
    0.79
     concurrently
    0.79
     lawfully
    0.77
     illegally
    0.74
     smoothly
    0.73
     successfully
    0.72
     jointly
    0.71
    ATING
    0.70
    eering
    0.70
    Activations Density 0.029%

    No Known Activations