© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 11772
    Prev
    Next
    INDEX
    Explanations

    instances of the sound "im" followed by different endings or context

    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
    406
    +0.13
    0.7%
    471
    +0.13
    0.7%
    397
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.06
    369
    +0.13
    0.02
    18
    +0.12
    0.05
    Negative Logits
    inib
    -1.88
    izable
    -1.72
    course
    -1.71
    ivities
    -1.53
    ĻĤ
    -1.47
    hift
    -1.46
     extent
    -1.43
    ¯
    -1.40
     amount
    -1.40
    ength
    -1.40
    POSITIVE LOGITS
    bler
    2.12
    ber
    2.04
    genstein
    1.90
    bling
    1.90
    ble
    1.86
    bed
    1.78
    bek
    1.76
    bet
    1.71
    ERTY
    1.69
    bsy
    1.67
    Activations Density 0.327%

    No Known Activations