© 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. 24275
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis and evaluation in research

    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
    156
    +0.43
    2.7%
    271
    +0.16
    1.0%
    240
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.43
    0.14
    47
    +0.16
    0.14
    61
    +0.14
    0.12
    Negative Logits
     affiliate
    -1.44
     outlet
    -1.35
    blogger
    -1.29
    Docket
    -1.27
     cam
    -1.25
     continuation
    -1.23
    EEK
    -1.20
     tv
    -1.18
     contradiction
    -1.15
    venth
    -1.14
    POSITIVE LOGITS
    Ļª
    3.21
    ĻĤ
    3.17
    ¼
    3.16
    ģ
    3.06
    ¯
    2.94
    ·¸
    2.85
    ł
    2.72
    Ļ
    2.67
    Ĭ
    2.63
    ļ
    2.60
    Activations Density 2.773%

    No Known Activations