© 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. 9028
    Prev
    Next
    INDEX
    Explanations

    details related to events and schedules

    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
    307
    +0.28
    1.7%
    306
    +0.20
    1.3%
    447
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.28
    0.08
    307
    +0.20
    0.14
    447
    +0.11
    0.09
    Negative Logits
     hasn
    -1.45
    wiki
    -1.41
    oubt
    -1.39
     isn
    -1.34
     rather
    -1.31
    fony
    -1.26
    jek
    -1.23
     doom
    -1.22
     insufficient
    -1.21
     doesnt
    -1.20
    POSITIVE LOGITS
    ↵↵
    5.20
    ↵
    5.20
    ↵
    5.20
    <|outofrange|>
    5.20
    5.20
    ↵
    5.20
     ↵
    5.20
    ↵
    5.20
    <|outofrange|>
    5.20
    5.20
    Activations Density 2.265%

    No Known Activations