© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26123
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags and structures

    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
    478
    +0.14
    0.8%
    438
    +0.13
    0.7%
    30
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.07
    17
    +0.13
    0.04
    192
    +0.12
    0.05
    Negative Logits
     herself
    -1.97
    ).](
    -1.69
    )](
    -1.52
    anya
    -1.52
    )].
    -1.50
    /#
    -1.50
    %).
    -1.46
    ocur
    -1.41
    ics
    -1.41
    ).)
    -1.40
    POSITIVE LOGITS
    ĨĴ
    1.67
    =========
    1.64
    =============
    1.50
     '</
    1.46
    rangle
    1.46
     browse
    1.43
    ===========
    1.41
     tents
    1.40
    ====================
    1.37
     banner
    1.36
    Activations Density 0.597%

    No Known Activations