© 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. 11888
    Prev
    Next
    INDEX
    Explanations

    legal terms and references

    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
    496
    +0.13
    0.6%
    346
    +0.12
    0.5%
    688
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.13
    0.02
    496
    +0.12
    0.02
    155
    +0.10
    0.02
    Negative Logits
    ACTED
    -0.68
     audible
    -0.66
    ibilities
    -0.65
     awa
    -0.64
     suscept
    -0.63
    hetic
    -0.63
     sequ
    -0.62
     retina
    -0.59
    atomic
    -0.59
     improvised
    -0.59
    POSITIVE LOGITS
    yer
    1.63
    yers
    1.47
    suit
    1.46
    rence
    1.44
    suits
    1.39
     Enforcement
    1.19
    makers
    1.19
    rences
    1.10
     enforcement
    1.05
    lessness
    1.02
    Activations Density 0.019%

    No Known Activations