© 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. 4-RES-SM
    11. 11498
    Prev
    Next
    INDEX
    Explanations

    terms related to automation and automatic processes

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.14
    0.8%
    156
    +0.12
    0.7%
    194
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.14
    0.03
    194
    +0.12
    0.01
    246
    +0.12
    0.03
    Negative Logits
    poons
    -2.15
    chaft
    -2.01
    lings
    -1.94
     liking
    -1.85
    how
    -1.66
    dings
    -1.63
    wick
    -1.63
    gian
    -1.62
    tons
    -1.59
     thereof
    -1.59
    POSITIVE LOGITS
    º
    3.63
    ¸
    3.43
    ¤
    3.39
    ·
    3.39
    ĺ
    3.37
    ļ
    3.33
    ĸ
    3.33
    ¢
    3.32
    Ĩ
    3.20
    «
    3.19
    Activations Density 0.280%

    No Known Activations