© 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. 13564
    Prev
    Next
    INDEX
    Explanations

    references to driving and related activities or actions

    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
    110
    +0.14
    0.8%
    156
    +0.14
    0.8%
    42
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.14
    0.02
    115
    +0.14
    0.02
    42
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.67
    «
    -2.23
    §
    -2.19
    ª
    -1.96
    Ĺ
    -1.95
    Ĥ¬
    -1.95
    Ķ
    -1.92
    ighed
    -1.84
    issen
    -1.83
    ¨
    -1.82
    POSITIVE LOGITS
    wheel
    1.96
    forward
    1.75
    ham
    1.75
     thru
    1.69
     motors
    1.68
    mill
    1.67
    tor
    1.65
    walker
    1.53
     wheels
    1.52
    atile
    1.51
    Activations Density 0.145%

    No Known Activations