© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    quotes or pieces of advice given by a fatherly figure

    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
    720
    +0.12
    0.6%
    503
    +0.10
    0.5%
    614
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.12
    0.02
    380
    +0.10
    0.01
    217
    +0.10
    0.01
    Negative Logits
    ĸļ
    -0.75
    ords
    -0.73
    orn
    -0.71
    ema
    -0.69
    DAQ
    -0.62
    ERG
    -0.60
    Profile
    -0.59
    oice
    -0.59
    FTWARE
    -0.58
    reen
    -0.58
    POSITIVE LOGITS
     alternatively
    1.27
     equival
    1.06
    thodox
    0.97
    Else
    0.76
    depending
    0.74
     alas
    0.74
    matically
    0.74
     worse
    0.74
     maybe
    0.72
     depending
    0.71
    Activations Density 0.019%

    No Known Activations