© 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. 14829
    Prev
    Next
    INDEX
    Explanations

    dialogue and interaction between characters

    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
    21
    +0.37
    2.3%
    397
    +0.15
    0.9%
    281
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.37
    0.07
    445
    +0.15
    0.06
    117
    +0.12
    0.11
    Negative Logits
    Ļª
    -3.16
    -2.67
    -2.67
    <|outofrange|>
    -2.67
         ↵
    -2.67
    ↵
    -2.67
    ↵
    -2.67
    ↵↵
    -2.67
    -2.67
    <|outofrange|>
    -2.67
    POSITIVE LOGITS
     them
    1.43
    amo
    1.36
     empty
    1.32
     they
    1.29
     destroys
    1.26
     poison
    1.23
     itself
    1.20
     scientists
    1.20
     him
    1.17
     drugs
    1.15
    Activations Density 3.037%

    No Known Activations