© 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 EvalsExportsinterp-engineNEWAPI 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. 28423
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and procedures

    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
    23
    +0.49
    3.1%
    478
    +0.17
    1.0%
    251
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.49
    0.14
    478
    +0.17
    -0.01
    63
    +0.12
    0.02
    Negative Logits
    "}](#
    -2.06
    ÃŃf
    -1.88
    pieces
    -1.86
    Rptr
    -1.85
    heets
    -1.83
    liga
    -1.82
    amics
    -1.78
    .
    -1.76
    tion
    -1.75
    -âĤ¬
    -1.75
    POSITIVE LOGITS
    woke
    2.26
     welcome
    2.07
    ]>
    1.76
     bree
    1.75
     mercy
    1.66
     helm
    1.60
     UN
    1.51
     closed
    1.49
     toast
    1.47
     transgender
    1.45
    Activations Density 2.551%

    No Known Activations