© 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. 25605
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
    135
    +0.16
    0.9%
    281
    +0.16
    0.9%
    470
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.16
    0.08
    281
    +0.16
    0.07
    84
    +0.14
    0.03
    Negative Logits
     nuts
    -1.82
     confidentiality
    -1.57
     timeline
    -1.51
     history
    -1.48
     blame
    -1.44
     validity
    -1.44
     thumbs
    -1.43
     genus
    -1.42
     supporting
    -1.42
     fans
    -1.41
    POSITIVE LOGITS
    erad
    1.79
    Ĥ¬
    1.74
    izumab
    1.70
    azar
    1.68
    Ń
    1.67
    places
    1.64
    onna
    1.60
    oxygen
    1.57
    oche
    1.57
    ±
    1.55
    Activations Density 0.681%

    No Known Activations