© 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. 31502
    Prev
    Next
    INDEX
    Explanations

    terms related to leadership or positions of authority

    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
    463
    +0.14
    0.8%
    431
    +0.10
    0.5%
    94
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.14
    0.03
    431
    +0.10
    0.02
    131
    +0.10
    0.02
    Negative Logits
    Ī
    -3.48
    ¢
    -3.47
    ¯
    -3.40
    ĥ½
    -3.25
    ©
    -3.23
    ª
    -3.22
    §
    -3.20
    ĵ
    -3.17
    ¦
    -3.17
    ķ
    -3.17
    POSITIVE LOGITS
    piece
    2.33
    quarters
    2.25
    shots
    2.14
    pieces
    2.13
    space
    2.11
    quart
    1.98
    ings
    1.95
    waters
    1.94
    sets
    1.90
    lights
    1.89
    Activations Density 0.148%

    No Known Activations