© 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. 25003
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer treatment and the effects of various drugs on cancer and infections

    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
    156
    +0.19
    1.0%
    320
    +0.12
    0.7%
    232
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.19
    0.00
    2
    +0.12
    0.01
    320
    +0.11
    0.01
    Negative Logits
    amed
    -1.71
    aliana
    -1.65
     sequenced
    -1.60
    wide
    -1.59
     Mathemat
    -1.56
    iki
    -1.55
    matched
    -1.53
    roe
    -1.53
    nen
    -1.48
    dorff
    -1.47
    POSITIVE LOGITS
    §
    2.76
    ¦
    2.52
    ¥
    2.49
    ĸ
    2.41
    ¤
    2.37
    ¨
    2.20
    Ł
    2.13
    Ĥ
    2.09
    ¾
    2.09
    ¢
    2.09
    Activations Density 0.051%

    No Known Activations