© 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 24576
    9. 8-RES_FS24576-JB
    11. 18891
    Prev
    Next
    INDEX
    Explanations

    words related to disagreements or conflicts stemming from misunderstandings or misconceptions

    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
    13
    +0.11
    0.5%
    408
    +0.11
    0.5%
    320
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.11
    0.02
    408
    +0.11
    0.02
    422
    +0.10
    0.01
    Negative Logits
     Fires
    -0.64
    xtap
    -0.62
    oak
    -0.62
    days
    -0.60
    æ©
    -0.58
     Bridges
    -0.57
     Transcript
    -0.57
    maximum
    -0.57
    plings
    -0.56
     stumble
    -0.56
    POSITIVE LOGITS
     than
    0.91
     akin
    0.83
     resembling
    0.83
     nor
    0.77
     whatsoever
    0.75
    ient
    0.73
    ifa
    0.73
     achievable
    0.69
     manageable
    0.69
     glamorous
    0.68
    Activations Density 0.022%

    No Known Activations