© 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. 29455
    Prev
    Next
    INDEX
    Explanations

    references to backend systems and architecture in discussions

    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
    156
    +0.24
    1.4%
    447
    +0.10
    0.6%
    88
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.24
    0.19
    156
    +0.10
    0.11
    271
    +0.10
    0.07
    Negative Logits
    ).](
    -1.71
    ky
    -1.56
    shore
    -1.49
    ifi
    -1.48
    .](
    -1.47
    chitz
    -1.47
     exception
    -1.40
    sic
    -1.40
     regards
    -1.39
    .’”
    -1.39
    POSITIVE LOGITS
    µ
    1.66
    watson
    1.64
    amics
    1.49
    fiddle
    1.48
    HEL
    1.46
    rics
    1.44
     generates
    1.44
    "}](#
    1.41
    bellum
    1.36
    edly
    1.35
    Activations Density 0.593%

    No Known Activations