© 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. 7756
    Prev
    Next
    INDEX
    Explanations

    the preposition 'to' followed by different verbs or objects

    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
    608
    +0.17
    0.8%
    218
    +0.11
    0.5%
    508
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.17
    0.03
    508
    +0.11
    0.01
    648
    +0.09
    0.01
    Negative Logits
    spawn
    -0.79
    changed
    -0.79
     [*
    -0.75
    inet
    -0.74
    Supported
    -0.73
    clips
    -0.73
    owed
    -0.71
    ette
    -0.70
    ©¶æ¥µ
    -0.70
    ended
    -0.70
    POSITIVE LOGITS
     brute
    0.78
     desperation
    0.78
     violence
    0.70
     mush
    0.69
     whichever
    0.68
     intimidation
    0.68
     exhaustion
    0.65
    psy
    0.65
     expend
    0.64
     prayer
    0.64
    Activations Density 0.043%

    No Known Activations