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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 922
    Prev
    Next
    INDEX
    Explanations

    mentions of communication methods like phone and email or statements about contact preferences

    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
    297
    +0.12
    0.5%
    481
    +0.10
    0.4%
    400
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.12
    0.04
    79
    +0.10
    0.04
    289
    +0.09
    0.01
    Negative Logits
    illard
    -0.77
    OIL
    -0.74
     Conclusion
    -0.73
    cakes
    -0.71
    stad
    -0.70
    Elf
    -0.67
    urther
    -0.66
     decad
    -0.66
    bush
    -0.66
    udo
    -0.65
    POSITIVE LOGITS
     phone
    1.55
     phones
    1.53
     cellphone
    1.51
     telephone
    1.50
    phone
    1.38
     radios
    1.30
     Telephone
    1.28
    phones
    1.28
     smartphones
    1.28
     Skype
    1.27
    Activations Density 0.601%

    No Known Activations