© 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. 7609
    Prev
    Next
    INDEX
    Explanations

    references to specific issues or episodes within a series of interconnected stories

    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
    191
    +0.11
    0.5%
    484
    +0.10
    0.5%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.11
    0.02
    173
    +0.10
    0.01
    484
    +0.10
    0.02
    Negative Logits
     def
    -0.78
     fled
    -0.75
     lag
    -0.74
     prey
    -0.73
     shrimp
    -0.68
     educated
    -0.68
     minded
    -0.67
     begg
    -0.66
     speakers
    -0.66
     toast
    -0.65
    POSITIVE LOGITS
    VII
    0.88
    letters
    0.84
    Stretch
    0.83
    1
    0.82
    III
    0.81
    lisher
    0.80
    ãĥīãĥ©
    0.80
    DVD
    0.79
    uesday
    0.78
    éŃĶ
    0.77
    Activations Density 0.024%

    No Known Activations