© 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. 9980
    Prev
    Next
    INDEX
    Explanations

    references to user accounts and account-related actions

    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
    357
    +0.14
    0.8%
    471
    +0.10
    0.6%
    18
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.14
    0.01
    471
    +0.10
    0.01
    343
    +0.10
    0.02
    Negative Logits
    Ĥ¬
    -2.38
    º
    -2.30
    ´
    -2.23
    IJ
    -2.16
    ³
    -2.08
    ·¸
    -2.05
    ¯
    -2.04
    ĨĴ
    -2.03
    µ
    -2.00
    ĸ
    -1.91
    POSITIVE LOGITS
    ancy
    2.33
    antry
    2.26
    holder
    2.11
     rece
    1.89
    holders
    1.80
     payable
    1.80
     holders
    1.80
    ants
    1.79
    manager
    1.78
    erred
    1.76
    Activations Density 0.182%

    No Known Activations