© 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. 4-RES-SM
    11. 8980
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'S' in varying contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    68
    +0.13
    0.8%
    271
    +0.12
    0.7%
    434
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.13
    0.07
    386
    +0.12
    0.03
    434
    +0.12
    0.05
    Negative Logits
    eon
    -1.93
    eer
    -1.85
    uary
    -1.84
    een
    -1.68
    mentation
    -1.68
    eur
    -1.61
    eurs
    -1.55
    estly
    -1.54
    tails
    -1.48
    hold
    -1.46
    POSITIVE LOGITS
    AMPLE
    2.18
    ylvan
    2.17
    ymbols
    2.16
    vens
    2.16
    aturated
    2.15
    PECT
    2.13
    lightly
    2.12
    ubl
    2.10
    uffix
    2.10
    ensitive
    2.10
    Activations Density 0.075%

    No Known Activations