© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12544
    Prev
    Next
    INDEX
    Explanations

    technical specifications or parameters

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    186
    +0.18
    1.1%
    12
    +0.16
    0.9%
    153
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.18
    0.03
    153
    +0.16
    0.07
    27
    +0.16
    0.11
    Negative Logits
    openh
    -1.63
    ón
    -1.52
    ung
    -1.51
    vre
    -1.50
    OTA
    -1.48
    blic
    -1.48
    eba
    -1.47
    ibo
    -1.46
    ÈĻ
    -1.42
    isión
    -1.41
    POSITIVE LOGITS
    %\
    1.57
     hats
    1.48
     teens
    1.48
     knots
    1.45
     ÃĤ
    1.40
    âī¥
    1.38
    ingly
    1.37
     coats
    1.35
     acres
    1.35
     feathers
    1.31
    Activations Density 5.954%

    No Known Activations