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. 26958
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and technical issues

    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
    +0.25
    1.5%
    22
    +0.12
    0.7%
    271
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.25
    0.02
    236
    +0.12
    0.03
    444
    +0.11
    0.04
    Negative Logits
    ]{.
    -1.42
     Qué
    -1.40
    ISM
    -1.39
     DISCLAIM
    -1.34
     Sac
    -1.33
     Line
    -1.33
     Story
    -1.33
    Kit
    -1.32
     License
    -1.30
     SERVICES
    -1.30
    POSITIVE LOGITS
    Ļª
    1.94
     <%=
    1.63
    udes
    1.47
     #{
    1.46
    uar
    1.45
    uary
    1.44
    inging
    1.42
    sible
    1.37
    ¥
    1.35
    tering
    1.34
    Activations Density 0.406%

    No Known Activations