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. 11147
    Prev
    Next
    INDEX
    Explanations

    code-related patterns and specific commands

    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
    373
    +0.22
    1.5%
    480
    +0.14
    1.0%
    459
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.22
    -0.07
    314
    +0.14
    -0.03
    365
    +0.10
    0.01
    Negative Logits
     Pigs
    -0.42
     Waste
    -0.40
     RELEASE
    -0.38
    utenberg
    -0.36
     Cthulhu
    -0.36
     Hebdo
    -0.35
     Taxes
    -0.34
     Protest
    -0.34
     2024
    -0.34
     Profit
    -0.33
    POSITIVE LOGITS
    د
    0.49
    ĺ
    0.44
    ®
    0.43
    į
    0.42
    ĸ
    0.41
     challeng
    0.41
    ÙĬ
    0.41
    Ķ
    0.41
    ·
    0.41
    Ń
    0.40
    Activations Density 1.567%

    No Known Activations