© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 10615
    Prev
    Next
    INDEX
    Explanations

    intensifiers that suggest a significant degree of something

    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
    2
    +0.12
    0.7%
    288
    +0.12
    0.7%
    14
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.12
    0.02
    249
    +0.12
    0.02
    288
    +0.12
    0.03
    Negative Logits
    ·¸
    -1.88
    ĸ
    -1.66
    Ĺ
    -1.63
    ¤
    -1.63
    ļ
    -1.60
    ĨĴ
    -1.59
    Ŀ
    -1.55
    ¥
    -1.49
    Ķ
    -1.48
    ¹
    -1.48
    POSITIVE LOGITS
     enough
    1.54
    asone
    1.48
    uate
    1.45
    kered
    1.44
     luck
    1.43
    ness
    1.38
    Than
    1.38
    uilt
    1.37
     frank
    1.36
    ty
    1.35
    Activations Density 0.115%

    No Known Activations