© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "ST" often related to locations or statuses

    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
    202
    +0.11
    0.6%
    450
    +0.11
    0.6%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.11
    0.01
    334
    +0.11
    0.02
    148
    +0.11
    0.01
    Negative Logits
    stituted
    -1.77
    nel
    -1.68
    ster
    -1.67
    ological
    -1.58
    ski
    -1.56
    stit
    -1.55
    versation
    -1.55
    bed
    -1.48
    gered
    -1.48
    stances
    -1.45
    POSITIVE LOGITS
    ©
    3.24
    ĨĴ
    3.11
    ¨
    3.08
    Ļ
    3.03
    Ħ
    3.02
    Ĥ¬
    3.00
    ĥ
    2.91
    ¯
    2.88
    Ń
    2.88
    »¿
    2.87
    Activations Density 0.050%

    No Known Activations