© 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. 28408
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific DNA sequence motifs

    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
    110
    +0.13
    0.7%
    451
    +0.12
    0.7%
    108
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.13
    0.02
    451
    +0.12
    0.01
    385
    +0.11
    0.02
    Negative Logits
    ferentially
    -1.92
    »
    -1.80
    Ĺ
    -1.73
    ij
    -1.72
    nd
    -1.71
    lect
    -1.69
    others
    -1.54
    obbsee
    -1.53
    ontal
    -1.52
     cref
    -1.52
    POSITIVE LOGITS
    falls
    1.98
    ERIAL
    1.82
     proceeds
    1.80
    ting
    1.80
    mosp
    1.74
     spreads
    1.56
    ELY
    1.51
    URES
    1.48
    she
    1.47
    mos
    1.46
    Activations Density 0.094%

    No Known Activations