© 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. 26774
    Prev
    Next
    INDEX
    Explanations

    references to play-related activities or 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
    540
    +0.12
    0.5%
    531
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.12
    0.03
    531
    +0.10
    0.02
    16
    +0.10
    0.02
    Negative Logits
     Beir
    -0.77
     Apost
    -0.66
     Unic
    -0.66
     persecut
    -0.64
     9000
    -0.64
     Mayhem
    -0.60
     campaigned
    -0.60
     burst
    -0.60
     scanned
    -0.59
     crippling
    -0.59
    POSITIVE LOGITS
    wright
    1.55
    ername
    1.26
    dates
    1.24
    testers
    1.17
    wr
    1.17
    lists
    1.15
    tes
    1.15
    grounds
    1.07
    fulness
    1.07
    things
    1.06
    Activations Density 0.027%

    No Known Activations