© 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. 13093
    Prev
    Next
    INDEX
    Explanations

    references to notable first occurrences or distinctions in various contexts

    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
    476
    +0.16
    0.9%
    128
    +0.13
    0.7%
    485
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.16
    0.07
    239
    +0.13
    0.06
    130
    +0.13
    0.06
    Negative Logits
    ¦
    -2.47
    ¡
    -2.32
    Ľ
    -2.04
    ¬
    -2.04
    °
    -2.03
    ĥ½
    -2.02
    §
    -2.02
    «
    -1.91
    İ
    -1.89
    Ĥ
    -1.88
    POSITIVE LOGITS
     ever
    2.81
     thing
    2.11
     surviving
    1.84
     since
    1.75
     to
    1.74
     person
    1.73
     official
    1.72
     edition
    1.70
     nationally
    1.66
     anyone
    1.63
    Activations Density 0.256%

    No Known Activations