© 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. 20085
    Prev
    Next
    INDEX
    Explanations

    information related to news events and legal matters involving individuals from different regions

    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
    373
    +0.21
    1.1%
    276
    +0.08
    0.4%
    165
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.21
    -0.01
    426
    +0.08
    0.04
    230
    +0.08
    0.03
    Negative Logits
    itiz
    -0.60
    ,,,,
    -0.55
     renown
    -0.53
     disciplines
    -0.53
     accessibility
    -0.52
    esthes
    -0.51
     assembly
    -0.51
    minist
    -0.50
    stood
    -0.50
     orth
    -0.50
    POSITIVE LOGITS
     Continued
    0.80
     WATCHED
    0.73
    yn
    0.72
    Read
    0.71
    zens
    0.68
    itbart
    0.67
    htaking
    0.67
    chin
    0.65
    iban
    0.65
    inion
    0.65
    Activations Density 0.134%

    No Known Activations