© 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. 24797
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically those that end with "berg."

    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%
    43
    +0.16
    0.9%
    119
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.18
    0.03
    363
    +0.16
    0.03
    191
    +0.13
    0.02
    Negative Logits
     definite
    -1.63
     certain
    -1.56
     unambiguous
    -1.52
     deaf
    -1.52
    PECT
    -1.48
     SUCH
    -1.45
     yet
    -1.43
     autoimmune
    -1.42
    onstr
    -1.40
     such
    -1.40
    POSITIVE LOGITS
    dorff
    2.10
    wald
    2.01
    ruptcy
    1.93
    lund
    1.92
    feld
    1.91
    stown
    1.90
    hof
    1.87
    endas
    1.86
    wagen
    1.85
    fors
    1.85
    Activations Density 0.117%

    No Known Activations