© 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. 1-RES-SM
    11. 27347
    Prev
    Next
    INDEX
    Explanations

    repeated reference to specific subjects and pronouns, particularly emphasizing the importance of "this" and "our"

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.30
    1.7%
    56
    +0.14
    0.8%
    323
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.30
    0.09
    137
    +0.14
    0.11
    362
    +0.12
    0.12
    Negative Logits
    <|outofrange|>
    -3.65
    ↵↵
    -3.65
     ↵
    -3.65
             ↵
    -3.65
     ↵
    -3.65
    -3.65
    ↵
    -3.65
           ↵
    -3.65
         ↵
    -3.65
    <|outofrange|>
    -3.65
    POSITIVE LOGITS
     ?
    1.68
    /~
    1.65
    ?
    1.61
     famous
    1.52
    )?
    1.50
    ?!
    1.50
    upal
    1.44
     countless
    1.43
     bothered
    1.39
     millenn
    1.33
    Activations Density 1.955%

    No Known Activations