© 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. 1-RES-SM
    11. 29138
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mark" in various contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    211
    +0.14
    0.8%
    176
    +0.13
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.14
    0.03
    334
    +0.13
    0.03
    385
    +0.12
    0.02
    Negative Logits
    Ĺ
    -3.87
    ĻĤ
    -3.60
    ĥ
    -3.48
    ı
    -3.41
    ĸ´
    -3.36
    Ī
    -3.27
    ²
    -3.26
    ¼
    -3.25
    Ĥ
    -3.21
    IJ
    -3.18
    POSITIVE LOGITS
    iewicz
    2.60
    edly
    2.38
    owitz
    2.27
    hole
    2.06
    down
    1.85
    aline
    1.78
    ître
    1.71
    sson
    1.70
    lund
    1.67
    elsen
    1.67
    Activations Density 0.074%

    No Known Activations