© 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. 1306
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    481
    +0.17
    0.8%
    430
    +0.17
    0.8%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.17
    0.05
    46
    +0.17
    0.04
    224
    +0.12
    0.04
    Negative Logits
    etheless
    -0.65
    é¾įå
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.60
    PsyNetMessage
    -0.60
     variance
    -0.59
    é¾įå¥ij士
    -0.59
     Mandatory
    -0.57
     chem
    -0.57
    dylib
    -0.56
    ankind
    -0.56
    POSITIVE LOGITS
     apologised
    0.93
     thanked
    0.84
    ovich
    0.83
    cott
    0.75
    iewicz
    0.74
     told
    0.73
    's
    0.73
    ersen
    0.73
    Äĩ
    0.71
     Presents
    0.71
    Activations Density 0.091%

    No Known Activations