© 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. 25295
    Prev
    Next
    INDEX
    Explanations

    conjunctions connecting ideas or phrases in a text

    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
    140
    +0.14
    0.8%
    311
    +0.14
    0.8%
    389
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.09
    140
    +0.14
    0.08
    389
    +0.13
    0.08
    Negative Logits
     definition
    -1.53
    head
    -1.50
     scope
    -1.49
     result
    -1.44
    nsic
    -1.42
    result
    -1.42
    hex
    -1.41
     counterpart
    -1.39
     counterparts
    -1.35
    stituted
    -1.34
    POSITIVE LOGITS
     vice
    1.72
    fitting
    1.66
     convers
    1.64
     sometimes
    1.52
     frankly
    1.47
     rewarding
    1.44
     importantly
    1.44
     patience
    1.43
    ...)
    1.42
     hopefully
    1.41
    Activations Density 0.411%

    No Known Activations