© 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. 12314
    Prev
    Next
    INDEX
    Explanations

    words related to banned or prohibited items and actions

    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
    419
    +0.16
    1.0%
    231
    +0.15
    0.9%
    198
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.16
    0.03
    231
    +0.15
    0.04
    419
    +0.14
    0.03
    Negative Logits
    ...)
    -1.37
     bail
    -1.33
    ported
    -1.33
     ")
    -1.29
     USD
    -1.29
    lessly
    -1.29
     convenience
    -1.25
    gener
    -1.22
    ...?"
    -1.22
     Kingdom
    -1.21
    POSITIVE LOGITS
    ±
    2.48
    ĸ
    2.30
    ¿½
    2.28
    µ
    2.24
    »
    2.24
    ª
    2.23
    ¾
    2.22
    ·¸
    2.18
    ¯
    2.15
    ĩ
    2.09
    Activations Density 0.281%

    No Known Activations