© 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. 1-RES-SM
    11. 27486
    Prev
    Next
    INDEX
    Explanations

    references to violations of laws and regulations

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.26
    1.4%
    484
    +0.12
    0.6%
    184
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.26
    0.03
    186
    +0.12
    0.01
    62
    +0.11
    0.03
    Negative Logits
    ubicin
    -1.65
     wasted
    -1.42
    -%
    -1.36
    ="../../../../../../
    -1.36
    ocytes
    -1.36
    umab
    -1.33
     mate
    -1.32
     vacation
    -1.30
     mates
    -1.30
    ctomy
    -1.30
    POSITIVE LOGITS
    į
    2.15
    Ī
    2.14
    Ļª
    2.12
    İ
    2.08
    ³
    2.04
    ¿
    2.04
    Ĩ
    2.02
    ¶
    1.95
    ĩ
    1.94
    Ľ
    1.91
    Activations Density 0.483%

    No Known Activations