© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27151
    Prev
    Next
    INDEX
    Explanations

    questions that start with "Is"

    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
    376
    +0.16
    0.9%
    337
    +0.12
    0.7%
    81
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.16
    0.03
    64
    +0.12
    0.03
    389
    +0.12
    0.03
    Negative Logits
    Ľ
    -2.57
    »¿
    -2.48
    ĥ
    -2.26
    ģ
    -2.15
    į
    -2.13
    Ĵ
    -2.12
    Ļ
    -2.09
    ¡
    -2.08
    »
    -2.07
    Ŀ
    -2.04
    POSITIVE LOGITS
    olated
    2.41
    ocyan
    2.14
    olation
    1.86
    opropyl
    1.80
    ol
    1.78
    olate
    1.68
    lington
    1.68
    chemia
    1.58
    abella
    1.52
    ocyanate
    1.50
    Activations Density 0.068%

    No Known Activations