© 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. 26281
    Prev
    Next
    INDEX
    Explanations

    references to file formats and their associated types

    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
    316
    +0.13
    0.7%
    59
    +0.12
    0.7%
    21
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.13
    -0.01
    165
    +0.12
    0.06
    151
    +0.12
    0.07
    Negative Logits
    à«ĩ
    -1.74
    otal
    -1.52
    isd
    -1.49
    jsp
    -1.48
    ookie
    -1.48
    mt
    -1.46
    UTH
    -1.44
    asa
    -1.44
    áĢ¬
    -1.44
     fide
    -1.43
    POSITIVE LOGITS
     flexible
    1.50
    apine
    1.47
    ellers
    1.43
     cultures
    1.40
    than
    1.39
    derer
    1.34
     Conrad
    1.33
     Lear
    1.33
     Schneider
    1.30
     Welsh
    1.29
    Activations Density 1.588%

    No Known Activations