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. 27057
    Prev
    Next
    INDEX
    Explanations

    references to natural products or substances

    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
    438
    +0.14
    0.8%
    208
    +0.13
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.14
    0.03
    438
    +0.13
    0.03
    392
    +0.11
    0.03
    Negative Logits
    Ĭ
    -1.84
    Ľ
    -1.79
    Į
    -1.67
    her
    -1.60
    artan
    -1.54
    ľ
    -1.52
    ucht
    -1.48
    oof
    -1.48
    equal
    -1.47
    ott
    -1.47
    POSITIVE LOGITS
    istic
    2.20
    istically
    2.08
    izations
    1.94
    isations
    1.93
     sciences
    1.92
    ness
    1.80
    isation
    1.72
    itat
    1.72
     denominator
    1.69
    izing
    1.69
    Activations Density 0.079%

    No Known Activations