© 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 EvalsExportsAPI 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. 28086
    Prev
    Next
    INDEX
    Explanations

    technical keywords related to software usage and versions

    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
    35
    +0.12
    0.7%
    241
    +0.11
    0.6%
    252
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.12
    252
    +0.11
    0.07
    240
    +0.11
    0.01
    Negative Logits
     primer
    -1.47
     precaution
    -1.47
    odo
    -1.44
    odal
    -1.40
    nem
    -1.36
    agraph
    -1.33
     checklist
    -1.33
     criteria
    -1.31
     Penal
    -1.30
    amental
    -1.27
    POSITIVE LOGITS
    ĥ
    3.84
    ľĵ
    3.69
    Ĥ
    3.67
    ¦
    3.64
    ¿
    3.54
    Ĵ
    3.42
    ĥ½
    3.31
    Ļª
    3.29
    Ĥ¬
    3.27
    ľ
    3.24
    Activations Density 1.078%

    No Known Activations