© 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. 2-RES-SM
    11. 9813
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical comparisons

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    186
    +0.16
    1.0%
    72
    +0.13
    0.7%
    400
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.16
    0.06
    202
    +0.13
    0.06
    157
    +0.12
    0.08
    Negative Logits
     numbers
    -1.63
     company
    -1.54
     briefs
    -1.42
     court
    -1.38
     word
    -1.35
    again
    -1.35
     again
    -1.34
     DH
    -1.34
    anie
    -1.34
    lem
    -1.33
    POSITIVE LOGITS
    inary
    1.67
    odot
    1.33
    rin
    1.33
     subd
    1.30
    KES
    1.29
     ERA
    1.29
    WARE
    1.29
    bread
    1.28
    +$
    1.27
    $-$
    1.26
    Activations Density 0.974%

    No Known Activations