© 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. 24852
    Prev
    Next
    INDEX
    Explanations

    references to web pages and their navigation elements

    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
    466
    +0.13
    0.7%
    132
    +0.11
    0.6%
    119
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.13
    0.01
    255
    +0.11
    0.02
    466
    +0.11
    0.02
    Negative Logits
     suppose
    -1.56
     monolayer
    -1.55
     NaCl
    -1.50
     dB
    -1.43
     Bonferroni
    -1.43
     MERCHANTABILITY
    -1.42
     monol
    -1.42
    $$\
    -1.41
     \*\*
    -1.39
     adiabatic
    -1.39
    POSITIVE LOGITS
    antry
    2.10
    oon
    1.79
    guid
    1.75
    views
    1.73
    hors
    1.65
    vez
    1.65
    ofs
    1.63
    zilla
    1.63
    notes
    1.61
    ados
    1.61
    Activations Density 0.091%

    No Known Activations