© 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. 26398
    Prev
    Next
    INDEX
    Explanations

    references to a specific licensing information or terms

    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
    +0.34
    2.0%
    267
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.34
    0.06
    170
    +0.12
    0.03
    267
    +0.12
    0.04
    Negative Logits
     forth
    -1.73
    panic
    -1.63
    bered
    -1.53
    ência
    -1.50
    nered
    -1.49
    nob
    -1.45
    pec
    -1.43
    fulness
    -1.41
    uated
    -1.40
    itism
    -1.40
    POSITIVE LOGITS
    ĨĴ
    2.89
    Ĵ
    2.29
    ¯
    2.08
    §
    2.03
    ®
    1.99
    ¬
    1.96
    Ģ
    1.96
    ´
    1.94
    ·
    1.88
    ij
    1.86
    Activations Density 0.314%

    No Known Activations