© 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. 27346
    Prev
    Next
    INDEX
    Explanations

    expressions indicating elevated levels or standards

    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
    457
    +0.12
    0.7%
    142
    +0.12
    0.7%
    338
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.12
    0.03
    266
    +0.12
    0.03
    152
    +0.12
    0.03
    Negative Logits
    ·¸
    -2.56
    Ī
    -2.39
    ¼
    -2.37
    Į
    -2.35
    ³
    -2.35
    ¬
    -2.27
    ´
    -2.26
    ĨĴ
    -2.19
    ½
    -2.17
    İ
    -2.17
    POSITIVE LOGITS
     than
    2.65
    Than
    2.18
    than
    2.12
     Than
    1.96
     degrees
    1.85
     degree
    1.68
     magnitude
    1.66
     levels
    1.65
     thresholds
    1.63
     sized
    1.61
    Activations Density 0.053%

    No Known Activations