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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1135
    Prev
    Next
    INDEX
    Explanations

    details related to the Moon, such as its surface, spacecraft missions, and scientific discoveries

    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
    762
    +0.12
    0.6%
    548
    +0.10
    0.4%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.10
    548
    +0.10
    0.05
    325
    +0.09
    0.07
    Negative Logits
    iability
    -0.74
    hirt
    -0.73
    OWN
    -0.72
    à¨
    -0.71
    weeney
    -0.70
    ooters
    -0.69
    epad
    -0.68
    WER
    -0.68
     pestic
    -0.67
    Score
    -0.66
    POSITIVE LOGITS
     orbiting
    1.36
     orbits
    1.20
    arium
    1.19
     orbit
    1.05
     habitable
    1.02
     asteroids
    0.99
    oid
    0.98
     Orbit
    0.97
    oids
    0.95
     Nebula
    0.94
    Activations Density 0.931%

    No Known Activations