© 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. 18442
    Prev
    Next
    INDEX
    Explanations

    names of fantasy characters and creatures

    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
    673
    +0.11
    0.5%
    756
    +0.10
    0.5%
    436
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.05
    232
    +0.10
    0.05
    659
    +0.10
    0.05
    Negative Logits
    depending
    -0.77
     suspic
    -0.71
    staking
    -0.71
    ailability
    -0.68
     misunder
    -0.67
     notor
    -0.65
     .)
    -0.63
     perspect
    -0.63
     exha
    -0.62
     behavi
    -0.61
    POSITIVE LOGITS
     Presents
    0.95
     (?,
    0.93
     âĵĺ
    0.90
    !:
    0.88
    :
    0.85
     Suite
    0.81
     Featuring
    0.81
     Orchestra
    0.78
     feat
    0.75
     Profile
    0.74
    Activations Density 0.289%

    No Known Activations