© 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 12288
    5. 8-RES_FS12288-JB
    6. 10821
    Prev
    Next
    INDEX
    Explanations

    detailed information about specific events or instances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    481
    +0.22
    1.0%
    410
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    569
    +0.22
    0.06
    66
    +0.11
    0.06
    300
    +0.10
    0.07
    Negative Logits
    aintain
    -0.70
     profession
    -0.68
     clutter
    -0.68
    ographies
    -0.67
     endif
    -0.65
    atible
    -0.65
    ieties
    -0.65
     grips
    -0.64
    yth
    -0.63
     professions
    -0.63
    POSITIVE LOGITS
     February
    0.72
    vertisement
    0.71
    20439
    0.71
     Nikki
    0.69
     September
    0.68
    nesday
    0.66
    efer
    0.65
     December
    0.65
     August
    0.65
     April
    0.64
    Activations Density 1.104%

    No Known Activations