© 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. 1-RES-SM
    11. 29448
    Prev
    Next
    INDEX
    Explanations

    occurrences of the date "May 9"

    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
    100
    +0.12
    0.7%
    410
    +0.11
    0.6%
    444
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    0.03
    444
    +0.11
    0.03
    43
    +0.11
    0.03
    Negative Logits
    £
    -1.82
    ¶
    -1.76
    ´
    -1.75
    °
    -1.74
    Ĥ¬
    -1.71
    ·
    -1.69
    ¢
    -1.58
     theaters
    -1.57
     quo
    -1.56
     adults
    -1.53
    POSITIVE LOGITS
    bourne
    1.75
    quette
    1.61
    hew
    1.61
    orem
    1.61
    ors
    1.60
    bach
    1.60
    thur
    1.60
    aceut
    1.58
    ney
    1.58
    berry
    1.58
    Activations Density 0.069%

    No Known Activations