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. 8670
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics, player profiles, and team news

    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
    497
    +0.13
    0.6%
    111
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.03
    497
    +0.11
    0.03
    241
    +0.10
    0.03
    Negative Logits
     interf
    -0.69
     moder
    -0.68
     thumbs
    -0.66
     Gim
    -0.64
     mic
    -0.61
     tolerance
    -0.61
     scanner
    -0.60
    stood
    -0.60
     numerical
    -0.60
    estic
    -0.60
    POSITIVE LOGITS
    2020
    1.03
    2016
    1.00
    2014
    1.00
    09
    0.97
    04
    0.97
    2017
    0.96
    02
    0.95
    2012
    0.95
    08
    0.95
    2011
    0.95
    Activations Density 0.035%

    No Known Activations