© 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. 25596
    Prev
    Next
    INDEX
    Explanations

    references to credit cards and related financial information

    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
    223
    +0.15
    0.9%
    262
    +0.13
    0.8%
    17
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.15
    0.09
    223
    +0.13
    0.07
    337
    +0.12
    0.06
    Negative Logits
    ±
    -1.85
    ı
    -1.75
    ©
    -1.70
    Ŀ
    -1.67
    ³
    -1.61
    ·
    -1.60
    ften
    -1.59
    ł
    -1.56
    MAKE
    -1.54
     some
    -1.49
    POSITIVE LOGITS
    alties
    1.86
    âĢŁ
    1.74
    "</
    1.73
    ÃŃs
    1.73
    piration
    1.67
    ató
    1.60
    osphere
    1.58
    heses
    1.57
    encia
    1.56
    lite
    1.54
    Activations Density 1.352%

    No Known Activations