© 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. 4-RES-SM
    11. 14719
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in legal or political contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    444
    +0.15
    0.9%
    91
    +0.14
    0.8%
    12
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.15
    0.08
    91
    +0.14
    0.07
    12
    +0.12
    0.07
    Negative Logits
    į
    -4.36
    ½
    -4.32
    ¾
    -4.25
    ¯
    -4.21
    Ĥ
    -4.20
    ¤
    -4.19
    Ħ
    -4.18
    ↵
    -4.08
    -4.08
    -4.08
    POSITIVE LOGITS
     were
    3.01
     are
    3.00
     belong
    2.91
     have
    2.76
     alike
    2.75
     differ
    2.65
     constitute
    2.60
     remain
    2.57
     represent
    2.51
     relate
    2.51
    Activations Density 1.506%

    No Known Activations