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. 26927
    Prev
    Next
    INDEX
    Explanations

    references to adults in 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
    156
    +0.24
    1.4%
    362
    +0.14
    0.8%
    407
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.24
    0.02
    445
    +0.14
    0.01
    362
    +0.13
    0.02
    Negative Logits
    иÑģ
    -1.64
    ched
    -1.49
    oci
    -1.48
    subseteq
    -1.47
    аÑģÑģ
    -1.45
    sible
    -1.43
    ĨĴ
    -1.40
    for
    -1.38
    defer
    -1.38
    еÑģ
    -1.38
    POSITIVE LOGITS
     lives
    1.78
     equivalents
    1.76
     remains
    1.73
    icides
    1.70
     living
    1.63
     dispute
    1.58
    ennial
    1.54
     basis
    1.54
    urious
    1.54
     quarters
    1.51
    Activations Density 0.059%

    No Known Activations