© 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. 24241
    Prev
    Next
    INDEX
    Explanations

    questions regarding capabilities or possibilities

    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
    +0.20
    1.1%
    478
    +0.17
    0.9%
    48
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.20
    0.03
    449
    +0.17
    0.02
    202
    +0.14
    0.03
    Negative Logits
    »¿
    -3.28
    ¢
    -2.67
    Ŀ
    -2.43
    ľ
    -2.29
    Ľ
    -2.22
    ·¸
    -2.21
    §
    -2.18
    ĥ
    -2.16
    ©
    -2.10
    °
    -2.09
    POSITIVE LOGITS
    't
    2.36
    othing
    1.68
    NOT
    1.61
    terbury
    1.60
     arbitrary
    1.50
     mine
    1.50
    complete
    1.48
    osure
    1.48
     yours
    1.47
    cels
    1.45
    Activations Density 0.063%

    No Known Activations