© 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. 29409
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics and measurements

    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
    46
    +0.13
    0.7%
    259
    +0.11
    0.6%
    280
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.13
    0.09
    13
    +0.11
    0.07
    46
    +0.11
    0.06
    Negative Logits
    undry
    -1.88
    \'
    -1.72
    hof
    -1.53
    âĢŁ
    -1.50
    rapeutic
    -1.50
    infty
    -1.47
    poons
    -1.47
    rian
    -1.41
    biamo
    -1.41
    weg
    -1.39
    POSITIVE LOGITS
    urred
    1.59
    isma
    1.44
    arum
    1.43
    ?_
    1.43
    1.35
     frustration
    1.32
    ???
    1.30
    ??
    1.28
     stam
    1.26
    ?).
    1.25
    Activations Density 1.751%

    No Known Activations