© 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. 26544
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical processes and errors

    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
    478
    +0.15
    0.9%
    420
    +0.12
    0.7%
    23
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.15
    0.02
    416
    +0.12
    0.02
    240
    +0.11
    0.01
    Negative Logits
    =”
    -1.57
    heets
    -1.45
    eting
    -1.44
    aptic
    -1.39
    ¥
    -1.34
     features
    -1.34
    papers
    -1.33
    cgi
    -1.32
     therm
    -1.31
    structural
    -1.30
    POSITIVE LOGITS
    ère
    1.65
     regard
    1.60
     regards
    1.60
     respect
    1.44
    -------------------------------------------------------
    1.39
    =====
    1.38
    :**
    1.37
    rceil
    1.37
     LORD
    1.36
     ages
    1.34
    Activations Density 0.138%

    No Known Activations