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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26649
    Prev
    Next
    INDEX
    Explanations

    references to cliffs or steep drops in various contexts

    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
    52
    +0.13
    0.6%
    99
    +0.13
    0.6%
    326
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.01
    326
    +0.13
    0.01
    52
    +0.13
    0.01
    Negative Logits
    ufact
    -0.93
    Interstitial
    -0.92
    natureconservancy
    -0.84
    rity
    -0.84
    Role
    -0.80
    IFA
    -0.78
    ãĤ±
    -0.75
    ADRA
    -0.75
    apolis
    -0.74
    CTV
    -0.69
    POSITIVE LOGITS
     ledge
    0.95
     cliffs
    0.94
     cliff
    0.94
     dwellings
    0.88
     slope
    0.86
    cutting
    0.84
     edge
    0.84
    edge
    0.83
    haven
    0.79
    faced
    0.79
    Activations Density 0.007%

    No Known Activations