© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 31985
    Prev
    Next
    INDEX
    Explanations

    elements related to software or version control processes

    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
    478
    +0.14
    0.8%
    53
    +0.13
    0.7%
    12
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.08
    438
    +0.13
    0.05
    450
    +0.12
    0.04
    Negative Logits
     [âĢ¦]
    -1.63
    ”).
    -1.57
    arte
    -1.55
    ).](
    -1.54
     Hernandez
    -1.44
    rapeut
    -1.43
    \]](
    -1.42
    olute
    -1.42
     Tokyo
    -1.41
    ")]
    -1.39
    POSITIVE LOGITS
    #
    1.76
    ł
    1.72
    ¾
    1.72
     morn
    1.59
    \%
    1.58
     flags
    1.56
    veis
    1.52
    #.
    1.52
    sible
    1.49
     msgid
    1.47
    Activations Density 0.385%

    No Known Activations