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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1602
    Prev
    Next
    INDEX
    Explanations

    links or instructions in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    640
    +0.24
    1.1%
    679
    +0.15
    0.7%
    6
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.24
    0.18
    640
    +0.15
    0.16
    679
    +0.12
    0.14
    Negative Logits
     instinct
    -0.79
     blowing
    -0.78
     exotic
    -0.77
     thrust
    -0.76
     overpowered
    -0.76
     paradox
    -0.75
     overpower
    -0.74
     potent
    -0.73
     snowball
    -0.73
     impression
    -0.72
    POSITIVE LOGITS
     Please
    1.51
     Alternatively
    1.51
     Otherwise
    1.48
     Additionally
    1.47
     Also
    1.41
     Depending
    1.33
     If
    1.33
     However
    1.30
     Each
    1.27
     Afterwards
    1.25
    Activations Density 1.268%

    No Known Activations