© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 196
    Prev
    Next
    INDEX
    Explanations

    short phrases related to reviewing or critiquing different topics

    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
    +0.35
    1.7%
    480
    +0.15
    0.8%
    372
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.35
    0.14
    143
    +0.15
    0.08
    6
    +0.12
    0.09
    Negative Logits
    hement
    -0.85
     antit
    -0.79
     estranged
    -0.77
    ensibly
    -0.75
     centrally
    -0.75
     footing
    -0.73
     diving
    -0.69
     transition
    -0.67
    abwe
    -0.67
     extrad
    -0.67
    POSITIVE LOGITS
    Anyway
    1.26
    Posted
    1.13
    Anonymous
    1.10
    posted
    1.03
    ³³³³³³³³³³³³³³³³
    1.01
    ³³³³
    1.01
    ³³³³³³³³
    0.98
    ³³³
    0.97
     Anyway
    0.96
    Seriously
    0.93
    Activations Density 0.329%

    No Known Activations