© 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. 6276
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences or legality

    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
    447
    +0.21
    1.0%
    125
    +0.11
    0.5%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.21
    0.09
    125
    +0.11
    0.07
    288
    +0.10
    0.09
    Negative Logits
    wolves
    -0.59
    ãĥ£
    -0.58
    å¼
    -0.58
    attle
    -0.56
    sych
    -0.56
    ZI
    -0.55
    proven
    -0.54
    rehens
    -0.54
    rov
    -0.53
    Billy
    -0.52
    POSITIVE LOGITS
     rul
    0.81
     anyway
    0.75
     nonetheless
    0.74
     insofar
    0.73
     indirectly
    0.72
     withd
    0.71
     uncond
    0.70
     destro
    0.69
     ALSO
    0.69
     indeed
    0.69
    Activations Density 0.883%

    No Known Activations