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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26972
    Prev
    Next
    INDEX
    Explanations

    terms related to screen display or GUI elements

    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
    +0.16
    0.9%
    502
    +0.13
    0.8%
    164
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.16
    0.02
    164
    +0.13
    0.02
    354
    +0.13
    0.02
    Negative Logits
    itiveness
    -1.83
    itively
    -1.77
     certain
    -1.67
    rophic
    -1.66
     particular
    -1.66
    rophe
    -1.60
     nervous
    -1.56
    lamide
    -1.52
     faith
    -1.50
     bond
    -1.49
    POSITIVE LOGITS
    casts
    2.31
    cast
    2.06
    caps
    2.01
    ings
    1.93
    plays
    1.91
    writer
    1.86
    ström
    1.83
    cloth
    1.77
    casting
    1.75
    play
    1.72
    Activations Density 0.107%

    No Known Activations