© 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. 8045
    Prev
    Next
    INDEX
    Explanations

    names of movies or TV shows

    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
    503
    +0.15
    0.7%
    232
    +0.10
    0.5%
    127
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.15
    0.02
    232
    +0.10
    0.02
    127
    +0.10
    0.01
    Negative Logits
    glers
    -0.75
    FP
    -0.69
    REF
    -0.65
     McCabe
    -0.63
    gerald
    -0.60
     Labrador
    -0.60
    åŃ
    -0.59
     climate
    -0.58
     phosphorus
    -0.58
    в
    -0.57
    POSITIVE LOGITS
    arkable
    1.26
    nants
    1.23
    ovable
    1.21
    oving
    1.19
    ittance
    1.19
    arks
    1.11
    ainer
    1.11
    edy
    1.11
    nant
    1.10
    ainers
    1.08
    Activations Density 0.010%

    No Known Activations