© 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. 37436
    Prev
    Next
    INDEX
    Explanations

    phrases that denote significant reasons or justifications 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
    114
    +0.10
    0.5%
    144
    +0.09
    0.4%
    715
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.10
    0.03
    604
    +0.09
    0.02
    533
    +0.09
    0.02
    Negative Logits
    lict
    -0.72
    esc
    -0.71
    inav
    -0.68
     Carbuncle
    -0.68
    ortunately
    -0.65
    ream
    -0.65
    chron
    -0.64
    qv
    -0.63
    ãĥĪ
    -0.62
    aith
    -0.62
    POSITIVE LOGITS
     why
    1.30
    why
    0.99
     WHY
    0.95
    abl
    0.91
     behind
    0.83
    pointers
    0.82
     cele
    0.79
    forward
    0.74
    Why
    0.73
     Why
    0.71
    Activations Density 0.017%

    No Known Activations