© 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. 26236
    Prev
    Next
    INDEX
    Explanations

    references to document files

    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
    410
    +0.15
    0.9%
    250
    +0.12
    0.7%
    188
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.15
    0.02
    95
    +0.12
    0.02
    139
    +0.11
    0.02
    Negative Logits
     Virgin
    -1.62
    IGH
    -1.60
     chances
    -1.57
     ASP
    -1.57
    ances
    -1.55
    IGHT
    -1.54
     dear
    -1.50
     subsequent
    -1.49
    ĥ½
    -1.49
     Assumption
    -1.48
    POSITIVE LOGITS
    strings
    2.01
    ryl
    1.80
    herty
    1.71
    iary
    1.61
    string
    1.61
    utils
    1.61
    entes
    1.56
    zent
    1.55
    ious
    1.54
    tools
    1.54
    Activations Density 0.122%

    No Known Activations