© 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. 25206
    Prev
    Next
    INDEX
    Explanations

    references to debugging processes or commands

    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
    +0.18
    1.0%
    295
    +0.12
    0.7%
    95
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.18
    0.02
    443
    +0.12
    0.02
    167
    +0.12
    0.02
    Negative Logits
    CO
    -1.61
    awk
    -1.54
    SI
    -1.51
    idazole
    -1.47
    idi
    -1.43
    nen
    -1.41
    chol
    -1.40
    agra
    -1.40
    onas
    -1.39
    uke
    -1.38
    POSITIVE LOGITS
    ger
    2.51
    ging
    2.29
    ged
    2.19
    gers
    2.07
    ±
    1.87
     info
    1.79
    Ń
    1.79
    ¡
    1.73
    ¦
    1.73
    İ
    1.72
    Activations Density 0.106%

    No Known Activations