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. 23448
    Prev
    Next
    INDEX
    Explanations

    words related to sweetness or sweet characteristics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    526
    +0.17
    0.8%
    459
    +0.11
    0.5%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.17
    0.01
    326
    +0.11
    0.01
    271
    +0.10
    0.01
    Negative Logits
    Downloadha
    -1.16
     Administ
    -0.79
    kson
    -0.78
    agher
    -0.70
     Occupations
    -0.68
    agall
    -0.66
     Uz
    -0.65
    senal
    -0.65
     Bakr
    -0.64
    NUM
    -0.64
    POSITIVE LOGITS
    heart
    1.45
    eners
    1.42
    ened
    1.34
    ener
    1.25
    ening
    1.17
    bread
    1.11
     potato
    1.11
    est
    1.08
    sweet
    0.96
     potatoes
    0.96
    Activations Density 0.017%

    No Known Activations