© 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. 4-RES-SM
    11. 14162
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bo"

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    477
    +0.15
    0.8%
    130
    +0.14
    0.8%
    279
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.15
    0.04
    130
    +0.14
    0.03
    284
    +0.13
    0.02
    Negative Logits
    mable
    -2.17
    nant
    -1.80
    matically
    -1.79
    nah
    -1.73
    née
    -1.68
    nas
    -1.63
    uous
    -1.60
     quantity
    -1.60
     quantities
    -1.59
    nad
    -1.57
    POSITIVE LOGITS
    oster
    2.08
    ards
    2.07
    asting
    2.05
    ilers
    2.03
    omers
    2.00
    chs
    1.97
    zza
    1.95
    obs
    1.92
    omer
    1.89
    asts
    1.88
    Activations Density 0.185%

    No Known Activations