© 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. 13081
    Prev
    Next
    INDEX
    Explanations

    references to legal roles and responsibilities within professional contexts

    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
    348
    +0.21
    1.2%
    410
    +0.15
    0.9%
    472
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.21
    0.09
    410
    +0.15
    0.08
    73
    +0.14
    0.10
    Negative Logits
    Ĥ¬
    -3.67
    ij
    -3.58
    ĵ
    -3.55
    ĺ
    -3.54
    Ĥ
    -3.52
    ¬
    -3.51
    <|outofrange|>
    -3.48
    ↵
    -3.48
    <|outofrange|>
    -3.48
              ↵
    -3.48
    POSITIVE LOGITS
    ship
    3.47
    ial
    3.15
    's
    2.60
    ially
    2.40
     who
    2.40
    ials
    2.39
    iale
    2.38
    uscript
    2.31
    ele
    2.29
    ships
    2.24
    Activations Density 1.499%

    No Known Activations