© 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. 26952
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical derivatives

    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
    270
    +0.14
    0.8%
    147
    +0.14
    0.8%
    208
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.01
    147
    +0.14
    0.01
    208
    +0.11
    0.01
    Negative Logits
    ¯
    -4.64
    ĻĤ
    -4.29
    Ľ
    -4.25
    ²
    -4.18
    Ĥ¬
    -4.17
    ±
    -4.13
    ľĵ
    -4.11
    Ł
    -4.11
    ĨĴ
    -4.10
    ¡
    -4.09
    POSITIVE LOGITS
    maker
    1.49
    ences
    1.48
    aments
    1.48
     flows
    1.41
    acies
    1.36
    iero
    1.35
     contradict
    1.34
    emic
    1.34
    heid
    1.33
    lit
    1.33
    Activations Density 0.117%

    No Known Activations