© 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. 37162
    Prev
    Next
    INDEX
    Explanations

    references to "Mail" or related terms in the context of digital communication

    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
    314
    +0.10
    0.4%
    373
    +0.10
    0.4%
    755
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.10
    0.01
    515
    +0.10
    0.01
    707
    +0.10
    0.01
    Negative Logits
    oulos
    -0.74
    ORN
    -0.73
    issan
    -0.72
     Strauss
    -0.69
     Haram
    -0.68
     Mercer
    -0.68
    ItemTracker
    -0.63
     Nob
    -0.61
    umbers
    -0.61
     Parables
    -0.60
    POSITIVE LOGITS
    bag
    1.06
    boxes
    1.06
    box
    1.05
    mail
    0.89
    bags
    0.85
    room
    0.85
    ing
    0.83
    Box
    0.77
    trap
    0.77
    UI
    0.76
    Activations Density 0.004%

    No Known Activations