© 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. 25291
    Prev
    Next
    INDEX
    Explanations

    references to states and their significance within the context provided

    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
    213
    +0.16
    0.9%
    199
    +0.13
    0.8%
    503
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.16
    0.04
    336
    +0.13
    0.04
    503
    +0.13
    0.04
    Negative Logits
    ij
    -3.78
    ĭ
    -3.55
    ±
    -3.51
    ª
    -3.31
    ·¸
    -3.18
    <|outofrange|>
    -3.13
    ↵
    -3.13
                ↵
    -3.13
    -3.13
    <|outofrange|>
    -3.13
    POSITIVE LOGITS
    oft
    1.78
    hood
    1.71
     affairs
    1.62
    oyer
    1.60
    etable
    1.58
    eless
    1.58
    ared
    1.57
    ibo
    1.56
    craft
    1.55
    ward
    1.52
    Activations Density 0.081%

    No Known Activations