© 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. 31260
    Prev
    Next
    INDEX
    Explanations

    occurrences of the "/" symbol in texts

    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
    200
    +0.14
    0.8%
    203
    +0.13
    0.7%
    280
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.14
    0.04
    452
    +0.13
    0.02
    18
    +0.11
    0.02
    Negative Logits
    ://
    -1.74
    **](#
    -1.68
    ugin
    -1.64
    ()</
    -1.62
    (@"
    -1.61
    **).
    -1.57
    ('/
    -1.46
    **),
    -1.45
    ump
    -1.44
    Demo
    -1.43
    POSITIVE LOGITS
    ¿
    3.59
    §
    3.54
    ¦
    3.49
    ¤
    3.47
    Ŀ
    3.32
    ·
    3.32
    »
    3.30
    IJ
    3.28
    ½
    3.25
    ł
    3.23
    Activations Density 0.066%

    No Known Activations