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. 29297
    Prev
    Next
    INDEX
    Explanations

    references to specific values and statistics

    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
    187
    +0.14
    0.8%
    156
    +0.14
    0.8%
    275
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.14
    0.03
    187
    +0.14
    0.02
    275
    +0.10
    0.01
    Negative Logits
    optera
    -1.66
     characterised
    -1.52
    cause
    -1.47
     arrest
    -1.47
     prescribed
    -1.46
    Exactly
    -1.44
    blogger
    -1.44
    onuclear
    -1.41
    disambiguation
    -1.40
     fault
    -1.40
    POSITIVE LOGITS
    erie
    1.87
    derr
    1.86
    oir
    1.83
    uet
    1.81
    dez
    1.74
    ved
    1.71
    asek
    1.66
    adin
    1.64
    inux
    1.61
    gus
    1.60
    Activations Density 0.150%

    No Known Activations