© 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 24576
    9. 8-RES_FS24576-JB
    11. 9353
    Prev
    Next
    INDEX
    Explanations

    words related to absorption, specifically in the context of materials absorbing energy or substances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    271
    +0.12
    0.5%
    375
    +0.10
    0.5%
    571
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.01
    570
    +0.10
    0.01
    571
    +0.10
    0.01
    Negative Logits
    oker
    -0.63
     Stronghold
    -0.62
    ;;;;;;;;;;;;
    -0.60
     Solitaire
    -0.60
     exoner
    -0.59
     revolving
    -0.58
    adders
    -0.56
    Egypt
    -0.56
     Egypt
    -0.55
    FTWARE
    -0.55
    POSITIVE LOGITS
    encies
    0.91
    ibles
    0.88
    iencies
    0.84
     absorbing
    0.81
    ency
    0.81
    tion
    0.81
     nutrients
    0.80
     absorbs
    0.76
     absorbed
    0.74
    icable
    0.73
    Activations Density 0.024%

    No Known Activations