© 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 49152
    9. 8-RES_FS49152-JB
    11. 37385
    Prev
    Next
    INDEX
    Explanations

    terms related to astronomy and astrophysics

    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
    578
    +0.11
    0.5%
    468
    +0.09
    0.4%
    144
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.11
    0.01
    468
    +0.09
    0.01
    701
    +0.09
    0.01
    Negative Logits
    tti
    -0.71
     voic
    -0.69
     Naj
    -0.62
     pestic
    -0.58
     done
    -0.58
     undone
    -0.57
    EFF
    -0.57
     scrut
    -0.56
     deaf
    -0.56
    à¨
    -0.56
    POSITIVE LOGITS
    autical
    1.14
    omical
    0.96
    oids
    0.87
    oid
    0.87
    ational
    0.86
    ogical
    0.85
    omers
    0.85
    etary
    0.81
    omics
    0.81
    omic
    0.80
    Activations Density 0.008%

    No Known Activations