© 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. 24690
    Prev
    Next
    INDEX
    Explanations

    references to reading and writing activities

    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
    174
    +0.12
    0.7%
    183
    +0.12
    0.7%
    301
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.12
    0.03
    183
    +0.12
    0.03
    503
    +0.12
    0.02
    Negative Logits
    Ł
    -4.93
    ľ
    -4.86
    ĥ½
    -4.69
    §
    -4.58
    ·
    -4.50
    ½
    -4.50
    ¤
    -4.49
    ı
    -4.48
    ĺ
    -4.46
    ķ
    -4.45
    POSITIVE LOGITS
     aloud
    2.30
     comprehension
    1.82
     glasses
    1.78
     headlines
    1.65
     aid
    1.62
     about
    1.60
    ied
    1.56
     About
    1.52
     books
    1.52
     Aid
    1.49
    Activations Density 0.136%

    No Known Activations