© 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. 25559
    Prev
    Next
    INDEX
    Explanations

    sequences of programmed symbols and keywords related to coding or technical specifications

    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
    23
    +0.21
    1.2%
    478
    +0.14
    0.8%
    495
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.21
    0.07
    346
    +0.14
    0.02
    74
    +0.12
    0.06
    Negative Logits
    ÃŃas
    -1.63
    flower
    -1.52
    ")]
    -1.49
    venir
    -1.48
    fan
    -1.47
    ño
    -1.45
     */,
    -1.44
    angel
    -1.42
    istor
    -1.41
    zyk
    -1.40
    POSITIVE LOGITS
    ĥ½
    2.60
    Ĺ
    2.47
    Ļ
    2.38
    ĵ
    2.32
    <|outofrange|>
    2.30
    2.30
     ↵
    2.30
    ↵Č
    2.30
    ↵
    2.30
    ↵
    2.30
    Activations Density 1.443%

    No Known Activations