© 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. 45886
    Prev
    Next
    INDEX
    Explanations

    words related to names and titles

    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
    288
    +0.12
    0.5%
    759
    +0.11
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.01
    683
    +0.11
    0.01
    288
    +0.10
    0.01
    Negative Logits
     elig
    -0.67
    stakes
    -0.66
    displayText
    -0.66
    BLIC
    -0.62
     luck
    -0.61
    TPP
    -0.58
     tense
    -0.57
    soDeliveryDate
    -0.57
    ZZ
    -0.56
    isition
    -0.55
    POSITIVE LOGITS
    oaded
    1.09
    phia
    1.04
    oad
    0.98
    anguage
    0.98
    phi
    0.93
    icate
    0.90
    adel
    0.89
    anguages
    0.89
    iberal
    0.88
    ittle
    0.87
    Activations Density 0.005%

    No Known Activations