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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 443
    Prev
    Next
    INDEX
    Explanations

    mention the word "online."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    481
    +0.13
    0.6%
    302
    +0.11
    0.5%
    656
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.19
    302
    +0.11
    0.12
    656
    +0.11
    0.09
    Negative Logits
    stones
    -0.87
    emi
    -0.85
    oi
    -0.84
    etta
    -0.83
    geist
    -0.81
    orious
    -0.79
    src
    -0.77
    wick
    -0.76
    older
    -0.76
    qs
    -0.75
    POSITIVE LOGITS
     computing
    0.93
     versions
    0.89
     imaging
    0.86
     gaming
    0.85
     storage
    0.85
     transportation
    0.84
     currencies
    0.83
     solutions
    0.83
     currency
    0.83
     recreation
    0.83
    Activations Density 2.836%

    No Known Activations