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. 1196
    Prev
    Next
    INDEX
    Explanations

    references to different forms of payment methods and financial transactions

    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
    481
    +0.28
    1.3%
    136
    +0.12
    0.5%
    743
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.09
    575
    +0.12
    0.08
    678
    +0.10
    0.05
    Negative Logits
     Rebell
    -0.67
    bernatorial
    -0.66
    ukong
    -0.64
    illard
    -0.62
    ptoms
    -0.60
    ibaba
    -0.58
    izens
    -0.58
     Klux
    -0.58
    akings
    -0.58
    andr
    -0.58
    POSITIVE LOGITS
     rather
    1.29
     instead
    1.20
    instead
    1.13
    rather
    1.04
     or
    0.92
    Instead
    0.79
     Instead
    0.78
     unless
    0.75
    Rather
    0.75
     whereas
    0.75
    Activations Density 0.592%

    No Known Activations