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. 2-RES-SM
    6. 29295
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly women

    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
    410
    +0.21
    1.2%
    503
    +0.15
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.21
    0.13
    503
    +0.15
    0.08
    369
    +0.14
    0.04
    Negative Logits
    etc
    -1.75
    erm
    -1.52
    rac
    -1.47
    stitutional
    -1.47
    legraph
    -1.46
    ram
    -1.44
    idential
    -1.44
    unto
    -1.41
    "/>
    -1.41
    onal
    -1.40
    POSITIVE LOGITS
     herself
    2.99
     Mae
    1.92
    udeau
    1.76
    issance
    1.76
     Louise
    1.70
     she
    1.69
    beth
    1.66
     gigg
    1.65
     Rice
    1.65
     Jane
    1.61
    Activations Density 0.821%

    No Known Activations