© 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. 9528
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly related to functions and their parameters

    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
    78
    +0.17
    1.0%
    21
    +0.15
    0.9%
    44
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.17
    0.10
    78
    +0.15
    0.01
    21
    +0.12
    0.05
    Negative Logits
    ĻĤ
    -4.34
    ¿½
    -3.94
    Ļª
    -3.44
    ĨĴ
    -3.27
    ľ
    -3.25
    ģ
    -3.18
    ·¸
    -3.08
    Īĺ
    -3.05
    ij
    -3.02
    Ĥ¬
    -3.01
    POSITIVE LOGITS
    ()
    2.73
    ().
    2.69
     ().
    2.68
    (),
    2.65
     ()
    2.42
    ".
    2.42
    ()"
    2.40
    ()))
    2.35
    ”.
    2.33
     (),
    2.31
    Activations Density 1.231%

    No Known Activations