© 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. 2-RES-SM
    11. 10620
    Prev
    Next
    INDEX
    Explanations

    instances of people in various contexts, particularly focusing on women and men, and their circumstances or actions

    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
    153
    +0.17
    1.0%
    156
    +0.13
    0.8%
    271
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.17
    0.00
    271
    +0.13
    -0.01
    365
    +0.13
    0.04
    Negative Logits
    vez
    -1.67
    omycin
    -1.55
     dissent
    -1.49
     critics
    -1.49
     ?
    -1.48
    ?,
    -1.44
     sort
    -1.39
    ¬
    -1.38
    âĢ²-
    -1.36
     Politics
    -1.34
    POSITIVE LOGITS
    inqu
    1.56
    bed
    1.51
    ĻĤ
    1.51
    cents
    1.47
    ctic
    1.44
     visits
    1.42
    assertEquals
    1.42
    cases
    1.41
    áĥĶ
    1.40
    hesis
    1.39
    Activations Density 0.605%

    No Known Activations