© 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 EvalsExportsAPI 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. 27436
    Prev
    Next
    INDEX
    Explanations

    mentions of elephants

    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
    203
    +0.15
    0.9%
    54
    +0.12
    0.7%
    171
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.02
    203
    +0.12
    0.02
    364
    +0.11
    0.01
    Negative Logits
     same
    -1.89
    ness
    -1.65
     authors
    -1.63
    same
    -1.57
     birth
    -1.49
    inherit
    -1.46
    equal
    -1.46
    olds
    -1.42
    speech
    -1.42
     paper
    -1.36
    POSITIVE LOGITS
    phant
    2.28
    venth
    2.24
    ¯
    2.12
    phants
    1.88
    ŀ
    1.73
    Ĵ
    1.67
    vation
    1.66
    Ľ
    1.65
    ł
    1.63
    ī
    1.61
    Activations Density 0.109%

    No Known Activations