© 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. 25198
    Prev
    Next
    INDEX
    Explanations

    numerical values related to biological or medical 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
    84
    +0.12
    0.7%
    374
    +0.10
    0.6%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.12
    0.02
    374
    +0.10
    0.02
    175
    +0.10
    0.02
    Negative Logits
     lane
    -1.51
     now
    -1.51
    uses
    -1.50
    itation
    -1.49
     round
    -1.38
    iss
    -1.36
    ience
    -1.35
    ient
    -1.34
    ipart
    -1.33
    it
    -1.33
    POSITIVE LOGITS
    ·
    1.84
    blogger
    1.58
    Ĥ
    1.58
    ¦
    1.53
    8859
    1.53
    Verlag
    1.50
    ului
    1.49
    families
    1.44
    album
    1.43
    arten
    1.42
    Activations Density 0.059%

    No Known Activations