© 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. 9781
    Prev
    Next
    INDEX
    Explanations

    instances of stagnation or lack of progress

    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
    9
    +0.10
    0.5%
    468
    +0.10
    0.5%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.10
    0.02
    9
    +0.10
    0.01
    236
    +0.09
    0.02
    Negative Logits
    arov
    -0.77
    ãĥĨãĤ£
    -0.69
    ãĥı
    -0.67
     oath
    -0.63
    BLIC
    -0.63
    ricular
    -0.63
    oho
    -0.62
    tains
    -0.62
    CVE
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.61
    POSITIVE LOGITS
     behind
    1.01
    luster
    0.84
     Behind
    0.83
    nesses
    0.80
    DOWN
    0.78
    lust
    0.77
    pid
    0.75
    staff
    0.70
    behind
    0.70
    beat
    0.69
    Activations Density 0.056%

    No Known Activations