© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3752
    Prev
    Next
    INDEX
    Explanations

    negative or critical assessments

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    297
    +0.13
    0.6%
    575
    +0.11
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.13
    0.03
    297
    +0.11
    0.03
    383
    +0.10
    0.03
    Negative Logits
    orks
    -0.83
    fs
    -0.74
     fixme
    -0.70
     Chains
    -0.69
    rib
    -0.66
    imeters
    -0.65
    haul
    -0.65
    NAS
    -0.64
    inders
    -0.64
    iaries
    -0.63
    POSITIVE LOGITS
     missing
    0.88
     lurking
    0.83
     else
    0.82
     happening
    0.82
     poetic
    0.78
     sinister
    0.76
     shameful
    0.76
     redeem
    0.76
     intrinsic
    0.76
     inherent
    0.75
    Activations Density 0.059%

    No Known Activations