© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7424
    Prev
    Next
    INDEX
    Explanations

    phrases related to NASA

    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
    447
    +0.13
    0.6%
    269
    +0.13
    0.6%
    346
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.13
    0.02
    346
    +0.13
    0.02
    296
    +0.12
    0.02
    Negative Logits
    cum
    -0.79
    tery
    -0.70
    stood
    -0.68
    âĶģ
    -0.67
    âĶĢâĶĢ
    -0.66
    otine
    -0.64
    letico
    -0.63
    oldemort
    -0.63
    olas
    -0.62
    tons
    -0.62
    POSITIVE LOGITS
     Goddard
    0.99
     Headquarters
    0.98
     astronauts
    0.93
     astronaut
    0.92
     Fisheries
    0.92
     Administrator
    0.86
     satellites
    0.85
     Ames
    0.84
     astronomers
    0.81
    ITED
    0.79
    Activations Density 0.023%

    No Known Activations