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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41348
    Prev
    Next
    INDEX
    Explanations

    references to technological applications and networks in various sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.55
    2.9%
    266
    +0.13
    0.7%
    481
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.55
    0.01
    363
    +0.13
    0.04
    384
    +0.11
    0.04
    Negative Logits
    named
    -0.61
    APTER
    -0.57
    argument
    -0.54
     Chaser
    -0.53
    amaz
    -0.50
     Ake
    -0.50
     "%
    -0.50
     Ratio
    -0.49
     msg
    -0.49
    NP
    -0.49
    POSITIVE LOGITS
    ospace
    0.82
     continents
    0.76
     satellites
    0.75
     museums
    0.73
    humans
    0.72
     workplaces
    0.72
     academia
    0.72
     humans
    0.71
     ecosystems
    0.71
     industries
    0.71
    Activations Density 0.262%

    No Known Activations