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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26753
    Prev
    Next
    INDEX
    Explanations

    instances of the word "release" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    217
    +0.14
    0.8%
    156
    +0.14
    0.8%
    308
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.14
    0.02
    217
    +0.14
    0.03
    490
    +0.13
    0.02
    Negative Logits
    ĨĴ
    -2.20
    ¼
    -2.13
    Į
    -2.00
    Ļª
    -1.87
    ĸ
    -1.87
    Ĵ
    -1.84
    ¹
    -1.82
    ĵ
    -1.77
    ĥ½
    -1.76
    ©
    -1.76
    POSITIVE LOGITS
    ments
    2.29
    ment
    1.98
    ional
    1.79
    ions
    1.78
    urized
    1.71
     date
    1.69
    ptions
    1.69
    ivity
    1.66
    able
    1.59
    icular
    1.59
    Activations Density 0.112%

    No Known Activations