© 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. 8795
    Prev
    Next
    INDEX
    Explanations

    references to specific concepts or practices within different belief systems or religions

    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
    480
    +0.51
    2.7%
    447
    +0.13
    0.7%
    266
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.51
    0.01
    266
    +0.13
    0.07
    362
    +0.12
    0.06
    Negative Logits
    *:
    -0.70
    !.
    -0.65
    !:
    -0.64
    +.
    -0.63
    ';
    -0.59
    .:
    -0.59
    :,
    -0.58
     although
    -0.57
    jri
    -0.53
    *.
    -0.53
    POSITIVE LOGITS
    pires
    0.79
    pired
    0.72
     differed
    0.48
     mattered
    0.48
    ihadi
    0.47
     might
    0.46
     FF
    0.45
     entails
    0.45
    Script
    0.44
     EVs
    0.44
    Activations Density 0.725%

    No Known Activations