© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 28113
    Prev
    Next
    INDEX
    Explanations

    references to legal courts and cases

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    410
    +0.15
    0.9%
    185
    +0.12
    0.7%
    74
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.02
    491
    +0.12
    0.02
    185
    +0.11
    0.01
    Negative Logits
    ?",
    -1.75
    CDATA
    -1.64
    )",
    -1.61
    "}](#
    -1.58
    ypse
    -1.58
    reek
    -1.55
    iph
    -1.49
    /"
    -1.46
    hemer
    -1.45
    ?”
    -1.45
    POSITIVE LOGITS
    ¶
    3.84
    ĻĤ
    3.84
    ´
    3.75
    ·
    3.67
    »
    3.62
    ģ
    3.61
    °
    3.55
    ¨
    3.49
    ¿
    3.47
    ·¸
    3.46
    Activations Density 0.097%

    No Known Activations