© 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. 24257
    Prev
    Next
    INDEX
    Explanations

    mentions of updates or edits in a document

    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
    482
    +0.13
    0.7%
    392
    +0.12
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.13
    0.01
    392
    +0.12
    0.02
    482
    +0.11
    0.01
    Negative Logits
    Ī
    -2.37
    ĥ½
    -2.26
    Ĭ
    -2.25
    Ľ
    -2.15
    acter
    -2.04
    Ļª
    -2.03
    ·¸
    -2.01
    ĨĴ
    -2.01
    ¿
    -1.99
    Ĥ¬
    -1.99
    POSITIVE LOGITS
     ours
    1.56
     rt
    1.39
    ITION
    1.38
     sanity
    1.35
    LINE
    1.35
    lr
    1.35
     Caption
    1.34
    TI
    1.34
    ACK
    1.32
    heses
    1.32
    Activations Density 0.130%

    No Known Activations