Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7673
    Prev
    Next
    INDEX
    Explanations

    tech-related terms such as 'filter', 'controller', 'beam', 'scanline', 'grappling', and 'precision aim'

    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
    345
    +0.11
    0.5%
    675
    +0.10
    0.5%
    765
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.11
    0.03
    133
    +0.10
    0.04
    181
    +0.10
    0.03
    Negative Logits
     Ner
    -0.86
     Ric
    -0.77
    SN
    -0.77
    baugh
    -0.75
     nerd
    -0.74
     ner
    -0.73
     barley
    -0.72
     Sic
    -0.72
     Bundy
    -0.71
     Crim
    -0.70
    POSITIVE LOGITS
    Element
    0.89
    Environment
    0.87
    TERN
    0.86
    environment
    0.84
     Element
    0.83
    element
    0.80
    artment
    0.79
    ECTION
    0.79
    section
    0.78
    incarn
    0.77
    Activations Density 0.180%

    No Known Activations