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. 2-RES-SM
    6. 29402
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to cancer, particularly malignant conditions and their characteristics

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    326
    +0.18
    1.0%
    366
    +0.14
    0.8%
    301
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.18
    0.07
    366
    +0.14
    0.08
    326
    +0.12
    0.04
    Negative Logits
     sustainability
    -1.85
     blockchain
    -1.69
     cooker
    -1.64
     bipartisan
    -1.60
     Obama
    -1.60
     security
    -1.60
     committees
    -1.59
     freedoms
    -1.57
     Âĵ
    -1.57
     rpm
    -1.57
    POSITIVE LOGITS
    ³
    2.70
    Ĺ
    2.62
    ²
    2.59
    ª
    2.52
    ¯
    2.48
    Ľ
    2.47
    Ł
    2.45
    »¿
    2.42
    ¨
    2.39
    ĥ½
    2.39
    Activations Density 1.269%

    No Known Activations