© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 768
    9. 8-RES_FS768-JB
    11. 684
    Prev
    Next
    INDEX
    Explanations

    phrases related to teamwork and sports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    6
    +0.14
    0.6%
    248
    +0.14
    0.6%
    255
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.18
    255
    +0.14
    0.12
    426
    +0.12
    0.10
    Negative Logits
    gettable
    -0.78
    asers
    -0.77
    etheless
    -0.77
    ciplinary
    -0.73
    anship
    -0.69
    °
    -0.67
    aser
    -0.66
    ocate
    -0.66
    ength
    -0.66
    efeated
    -0.65
    POSITIVE LOGITS
     âĢķ
    1.20
     ["
    1.01
    [/
    0.99
    /"
    0.99
     [/
    0.83
     referring
    0.83
     Adds
    0.81
     Translation
    0.76
     Asked
    0.75
     Sounds
    0.74
    Activations Density 2.168%

    No Known Activations