© 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 EvalsExportsAPI 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. 27822
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "sing" in various 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/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
    457
    +0.14
    0.8%
    164
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.02
    392
    +0.13
    0.02
    59
    +0.12
    0.02
    Negative Logits
    itrile
    -1.45
     ove
    -1.43
    umen
    -1.42
     mammary
    -1.40
    NOT
    -1.40
    undy
    -1.38
     ignoring
    -1.37
     worrying
    -1.36
    eah
    -1.36
    focus
    -1.35
    POSITIVE LOGITS
    leton
    2.31
    apore
    2.19
    letons
    2.03
    along
    1.82
    enced
    1.70
    erville
    1.70
    chen
    1.67
    liga
    1.61
    ers
    1.61
    bank
    1.60
    Activations Density 0.148%

    No Known Activations