© 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. 1-RES-SM
    11. 27639
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific character, referring to the mention of "Cl" in various contexts

    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
    369
    +0.18
    1.0%
    410
    +0.15
    0.9%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.18
    0.03
    281
    +0.15
    0.03
    447
    +0.12
    0.02
    Negative Logits
    ĸ
    -1.91
    »¿
    -1.89
    ľĵ
    -1.79
     speedy
    -1.47
    bral
    -1.46
     hurry
    -1.45
    nergy
    -1.45
    ÑĤÑĮ
    -1.43
    ĸ´
    -1.42
    ccess
    -1.39
    POSITIVE LOGITS
    enin
    1.66
     evaluated
    1.64
    ones
    1.63
     screened
    1.56
    osed
    1.54
    arity
    1.53
    oven
    1.52
    affe
    1.48
    uet
    1.48
    oser
    1.45
    Activations Density 0.061%

    No Known Activations