© 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. 37386
    Prev
    Next
    INDEX
    Explanations

    references to air-related topics, particularly military or operational 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
    464
    +0.11
    0.5%
    288
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    758
    +0.11
    0.01
    152
    +0.11
    0.01
    364
    +0.10
    0.01
    Negative Logits
    aido
    -0.73
     Kuh
    -0.72
    ktop
    -0.69
     Blasio
    -0.60
    ario
    -0.60
    enty
    -0.60
     CLSID
    -0.59
     Millenn
    -0.59
    CRIPTION
    -0.59
    qqa
    -0.58
    POSITIVE LOGITS
    bnb
    1.10
    waves
    1.05
    planes
    0.87
    plane
    0.86
    lift
    0.81
    craft
    0.80
    casting
    0.77
    pan
    0.75
    bender
    0.73
    lock
    0.73
    Activations Density 0.008%

    No Known Activations