© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 25744
    Prev
    Next
    INDEX
    Explanations

    narratives involving conflict and magical elements

    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
    373
    +0.18
    0.9%
    494
    +0.10
    0.5%
    161
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.18
    0.02
    161
    +0.10
    0.01
    582
    +0.10
    0.01
    Negative Logits
    undy
    -0.81
    Advertisements
    -0.80
    ascript
    -0.73
    âĹ¼
    -0.69
    HL
    -0.68
    etts
    -0.66
    imer
    -0.65
    ariat
    -0.65
    eness
    -0.65
    ELY
    -0.65
    POSITIVE LOGITS
     Seeking
    0.65
     confronts
    0.64
     Makoto
    0.62
     learns
    0.62
    adiator
    0.59
     fugitive
    0.58
     Takeru
    0.58
     tensions
    0.57
    Untitled
    0.57
    Adds
    0.56
    Activations Density 0.040%

    No Known Activations