© 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 24576
    9. 8-RES_FS24576-JB
    11. 12069
    Prev
    Next
    INDEX
    Explanations

    neutral descriptive terms or statements

    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
    213
    +0.12
    0.5%
    688
    +0.11
    0.5%
    642
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.12
    0.02
    236
    +0.11
    0.03
    688
    +0.11
    0.03
    Negative Logits
     streng
    -0.67
    avorite
    -0.67
    wana
    -0.65
    idden
    -0.62
    habi
    -0.61
    ascus
    -0.61
    airs
    -0.61
    iverpool
    -0.61
    sung
    -0.61
    asca
    -0.61
    POSITIVE LOGITS
    uality
    1.11
    ually
    1.05
    orial
    1.04
    ional
    1.03
    fulness
    0.78
    finder
    0.78
    oids
    0.76
    ual
    0.76
    liest
    0.75
    uation
    0.74
    Activations Density 0.027%

    No Known Activations