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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11731
    Prev
    Next
    INDEX
    Explanations

    references to large-scale systems or operations

    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
    45
    +0.17
    1.0%
    198
    +0.12
    0.7%
    327
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.17
    0.03
    45
    +0.12
    0.03
    14
    +0.12
    0.04
    Negative Logits
    rile
    -1.90
    etine
    -1.56
    ilde
    -1.52
    ETHOD
    -1.51
    ÑĥÑĩ
    -1.48
     prompt
    -1.48
    riev
    -1.47
     dawn
    -1.46
    ICES
    -1.45
    ierno
    -1.44
    POSITIVE LOGITS
     (\>
    2.60
     amounts
    2.36
     (âī¥
    2.29
     (>
    2.29
     (\~
    2.17
     enough
    2.11
     sized
    2.10
     proportions
    2.06
     quantities
    2.05
     amount
    1.95
    Activations Density 0.099%

    No Known Activations