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. 23618
    Prev
    Next
    INDEX
    Explanations

    terms related to chemistry and chemical industry entities

    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
    116
    +0.12
    0.5%
    271
    +0.11
    0.5%
    212
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.01
    508
    +0.11
    0.01
    116
    +0.10
    0.01
    Negative Logits
     Bucs
    -0.69
    lihood
    -0.68
     Bridgewater
    -0.63
     Ferry
    -0.62
     Hood
    -0.61
     Eston
    -0.61
     Aud
    -0.60
     Islanders
    -0.60
     redes
    -0.59
     Ducks
    -0.59
    POSITIVE LOGITS
    istry
    1.27
    icals
    1.18
    chem
    1.08
    istries
    1.01
    otherapy
    0.99
    ologist
    0.92
    icians
    0.91
    Chem
    0.90
     chemistry
    0.89
    uria
    0.89
    Activations Density 0.025%

    No Known Activations