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. 11656
    Prev
    Next
    INDEX
    Explanations

    individuals who are influential or noteworthy in specific fields or contexts

    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
    263
    +0.17
    1.0%
    56
    +0.15
    0.9%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.13
    56
    +0.15
    -0.01
    331
    +0.14
    0.08
    Negative Logits
    itory
    -1.61
    iom
    -1.57
    OPLE
    -1.56
    ^](#
    -1.54
    isons
    -1.46
    ){#
    -1.43
    zione
    -1.42
    ]:
    -1.42
    :`
    -1.41
    ICT
    -1.40
    POSITIVE LOGITS
     himself
    2.34
    himself
    2.10
     his
    1.80
     beard
    1.63
    Willi
    1.62
     wife
    1.56
    stood
    1.46
     sparing
    1.46
     joking
    1.40
     bald
    1.35
    Activations Density 1.782%

    No Known Activations