© 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. 2-RES-SM
    11. 13103
    Prev
    Next
    INDEX
    Explanations

    instances of first-person references and expressions of uncertainty or prediction

    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
    143
    +0.14
    0.8%
    499
    +0.14
    0.8%
    153
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    229
    +0.14
    0.07
    143
    +0.14
    0.04
    246
    +0.14
    0.06
    Negative Logits
    Īĺ
    -2.85
    Ń
    -2.53
    ľĵ
    -2.53
    Ĥ
    -2.49
    ĨĴ
    -2.47
    ¨
    -2.47
    ²
    -2.45
    ĭ
    -2.42
    Ļª
    -2.38
    §
    -2.35
    POSITIVE LOGITS
    ahoma
    1.61
    arty
    1.49
    oman
    1.43
    orth
    1.41
    king
    1.40
    anting
    1.40
    anted
    1.38
    asp
    1.36
    AH
    1.35
    ah
    1.32
    Activations Density 0.783%

    No Known Activations