© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12884
    Prev
    Next
    INDEX
    Explanations

    expressions related to joy

    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
    314
    +0.16
    0.7%
    271
    +0.13
    0.6%
    504
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.16
    0.02
    334
    +0.13
    0.01
    151
    +0.10
    0.01
    Negative Logits
    pta
    -0.63
     penal
    -0.63
     stricter
    -0.63
     underest
    -0.59
     damning
    -0.59
     porous
    -0.58
    iban
    -0.57
     stringent
    -0.57
     adamant
    -0.57
     imperfect
    -0.56
    POSITIVE LOGITS
    fully
    1.48
    sticks
    1.46
    ous
    1.34
    ously
    1.33
    ride
    1.16
    iously
    1.15
    joy
    1.09
    ful
    1.03
    fulness
    1.03
    rous
    1.00
    Activations Density 0.023%

    No Known Activations