© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 14069
    Prev
    Next
    INDEX
    Explanations

    instances of the substring "st"

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    360
    +0.12
    0.7%
    444
    +0.12
    0.7%
    43
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.12
    0.03
    361
    +0.12
    0.03
    444
    +0.12
    0.01
    Negative Logits
    ¥
    -2.38
    ĸ´
    -2.35
    ·¸
    -2.33
    ¶
    -2.27
    ²
    -2.23
    µ
    -2.19
    Ķ
    -2.16
    Ĥ
    -2.14
    ¡
    -2.13
    ¿½
    -2.12
    POSITIVE LOGITS
    rike
    1.92
    retch
    1.80
    reams
    1.74
    ension
    1.70
    orb
    1.63
    ensibly
    1.61
    rolled
    1.61
    robe
    1.58
    aurant
    1.55
    eles
    1.55
    Activations Density 0.105%

    No Known Activations