© 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. 27407
    Prev
    Next
    INDEX
    Explanations

    specific non-English language characters or symbols

    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
    457
    +0.18
    1.0%
    410
    +0.16
    0.9%
    23
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.18
    271
    +0.16
    0.08
    156
    +0.15
    0.09
    Negative Logits
    pan
    -1.69
    estock
    -1.63
    ceptible
    -1.61
    ↵
    -1.59
    amiento
    -1.59
    iliary
    -1.58
    atory
    -1.54
    orship
    -1.53
    lot
    -1.52
    engers
    -1.47
    POSITIVE LOGITS
    ²
    2.60
    ĻĤ
    2.46
    Ī
    2.39
    «
    2.38
    ·
    2.28
    Į
    2.27
    ©
    2.23
    ª
    2.07
    ģ
    2.02
    ³
    1.98
    Activations Density 0.472%

    No Known Activations