© 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. 28801
    Prev
    Next
    INDEX
    Explanations

    references to the author William Faulkner

    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
    98
    +0.11
    0.6%
    258
    +0.11
    0.6%
    450
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.11
    0.02
    345
    +0.11
    0.02
    258
    +0.10
    0.02
    Negative Logits
     toast
    -1.60
     anybody
    -1.55
     deaf
    -1.53
     Mine
    -1.50
    ]>
    -1.46
    unnumbered
    -1.46
     BGCOLOR
    -1.41
     UPS
    -1.40
     sqlite
    -1.40
    "?"
    -1.38
    POSITIVE LOGITS
    jee
    2.18
    ström
    2.14
    itat
    2.12
    istas
    2.10
    vironment
    2.01
    stown
    2.00
    hood
    1.99
    stadt
    1.95
    recht
    1.93
    estead
    1.92
    Activations Density 0.108%

    No Known Activations