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. 11241
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'a'

    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
    36
    +0.27
    1.3%
    263
    +0.13
    0.6%
    636
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.27
    0.14
    250
    +0.13
    0.07
    636
    +0.12
    0.07
    Negative Logits
     advis
    -0.76
    grounds
    -0.76
     guides
    -0.72
     encour
    -0.71
     administrators
    -0.69
    mods
    -0.69
    external
    -0.68
    quickShipAvailable
    -0.68
     advocates
    -0.68
     intentions
    -0.67
    POSITIVE LOGITS
     bunch
    1.22
     handful
    1.20
     lot
    1.14
     few
    1.11
     dozen
    1.10
     chunk
    1.04
     portion
    1.04
     couple
    1.01
     whopping
    1.00
     slew
    1.00
    Activations Density 0.257%

    No Known Activations