© 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. 18616
    Prev
    Next
    INDEX
    Explanations

    mentions of user profiles and online interactions

    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
    640
    +0.23
    1.0%
    6
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.09
    6
    +0.10
    0.07
    107
    +0.10
    0.05
    Negative Logits
     estranged
    -0.84
     photograp
    -0.79
     staggered
    -0.71
     fleeing
    -0.71
     pitching
    -0.70
     purs
    -0.69
     orchestr
    -0.69
     libraries
    -0.69
     predec
    -0.69
     escaping
    -0.69
    POSITIVE LOGITS
    Posted
    1.36
    Reply
    1.35
    ________________
    1.34
    User
    1.28
    Guest
    1.23
    Anonymous
    1.20
    anon
    1.16
    Edited
    1.16
    Anyway
    1.14
    Comment
    1.10
    Activations Density 0.189%

    No Known Activations