© 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. 6314
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and infrastructure, such as "return stack," "programming languages," and "building requirements."

    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
    314
    +0.14
    0.7%
    745
    +0.11
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.14
    0.05
    540
    +0.11
    0.05
    526
    +0.10
    0.01
    Negative Logits
     Monstrous
    -0.71
    IZE
    -0.67
    eger
    -0.64
     Flame
    -0.62
     Ruins
    -0.60
     Administrator
    -0.59
     Places
    -0.59
     Known
    -0.59
    theless
    -0.57
     Aires
    -0.57
    POSITIVE LOGITS
    ups
    1.22
    outs
    1.22
    away
    1.20
    ings
    1.18
    downs
    1.17
    backs
    1.16
    down
    1.16
    aways
    1.12
    up
    1.11
    out
    1.08
    Activations Density 0.260%

    No Known Activations