© 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. 28688
    Prev
    Next
    INDEX
    Explanations

    instances of user actions related to clicking

    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
    82
    +0.12
    0.7%
    99
    +0.12
    0.7%
    509
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.12
    0.03
    82
    +0.12
    0.03
    37
    +0.12
    0.03
    Negative Logits
    Ŀ
    -3.02
    ł
    -2.67
    ĻĤ
    -2.55
    ½
    -2.54
    ¦
    -2.48
    ¸
    -2.45
    ľ
    -2.44
    ļ
    -2.39
    ³
    -2.35
    ķ
    -2.35
    POSITIVE LOGITS
     ons
    1.74
    box
    1.66
    oslav
    1.64
    blogger
    1.63
    leader
    1.59
    rick
    1.57
    along
    1.57
    ings
    1.56
    ous
    1.53
    oned
    1.51
    Activations Density 0.052%

    No Known Activations