© 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. 26705
    Prev
    Next
    INDEX
    Explanations

    references to custody or care situations involving children

    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
    17
    +0.13
    0.7%
    56
    +0.13
    0.7%
    480
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.13
    0.12
    56
    +0.13
    -0.01
    234
    +0.10
    0.10
    Negative Logits
    gery
    -1.55
    creation
    -1.52
    ments
    -1.51
    rays
    -1.45
     scientists
    -1.44
     reasons
    -1.43
    idents
    -1.43
     evidenced
    -1.41
    ality
    -1.40
     purposes
    -1.39
    POSITIVE LOGITS
    stown
    1.80
     forefront
    1.76
     vicinity
    1.72
    bay
    1.67
    tin
    1.63
     outskirts
    1.63
    sburg
    1.62
    »¿
    1.59
     discretion
    1.58
    Īĺ
    1.57
    Activations Density 2.054%

    No Known Activations