© 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. 2-RES-SM
    11. 12955
    Prev
    Next
    INDEX
    Explanations

    Java package declarations and related import statements

    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
    63
    +0.13
    0.8%
    220
    +0.13
    0.7%
    320
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.13
    0.05
    501
    +0.13
    0.03
    37
    +0.13
    0.04
    Negative Logits
     (**
    -1.54
    ?",
    -1.48
    prototype
    -1.41
    goto
    -1.39
    tic
    -1.38
    oxford
    -1.36
    **),
    -1.36
    ”,
    -1.36
     crossover
    -1.35
    )',
    -1.34
    POSITIVE LOGITS
    Ģ
    2.53
    ¬
    2.32
    Ĥ¬
    2.20
    ij
    2.18
    ĥ½
    2.16
    ĨĴ
    2.16
    Īĺ
    2.15
    º
    2.14
    ĭ
    2.14
    ģ
    2.08
    Activations Density 0.214%

    No Known Activations