© 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. 28370
    Prev
    Next
    INDEX
    Explanations

    punctuation or periods

    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
    143
    +0.15
    0.8%
    426
    +0.14
    0.8%
    132
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.27
    156
    +0.14
    0.13
    271
    +0.12
    0.13
    Negative Logits
    imon
    -1.54
     offer
    -1.50
    anno
    -1.48
    intage
    -1.45
    wered
    -1.38
    LETE
    -1.37
    aney
    -1.33
    eva
    -1.30
    yet
    -1.30
    mlin
    -1.30
    POSITIVE LOGITS
    ½
    1.73
    ķ
    1.71
    ²
    1.64
    uginosa
    1.54
     wrong
    1.52
     untreated
    1.51
    ophilic
    1.46
    rapeut
    1.43
    problem
    1.42
    ¢
    1.42
    Activations Density 0.185%

    No Known Activations