© 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. 11219
    Prev
    Next
    INDEX
    Explanations

    terms related to ecological or environmental themes

    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
    21
    +0.16
    0.9%
    337
    +0.16
    0.9%
    83
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.16
    0.03
    337
    +0.16
    0.02
    218
    +0.15
    0.02
    Negative Logits
    hift
    -1.68
     loss
    -1.58
    pread
    -1.47
    hood
    -1.46
    abouts
    -1.43
     heartbeat
    -1.41
     quo
    -1.40
     trial
    -1.38
    INGTON
    -1.37
     mistrial
    -1.35
    POSITIVE LOGITS
    IJ
    3.39
    ĻĤ
    3.36
    Ĵ
    3.35
    «
    3.31
    ģ
    3.23
    ı
    3.20
    ¥
    3.16
    £
    3.08
    ĥ
    3.08
    ¢
    3.04
    Activations Density 0.141%

    No Known Activations