© 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. 10198
    Prev
    Next
    INDEX
    Explanations

    calls to action or engagement in the text

    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
    +0.25
    1.4%
    156
    +0.18
    1.0%
    369
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.25
    0.05
    485
    +0.18
    0.05
    38
    +0.17
    0.08
    Negative Logits
    "}](#
    -2.12
     compared
    -1.69
    ystems
    -1.63
    __.
    -1.61
    ){#
    -1.42
     thereto
    -1.42
    .*;
    -1.41
    he
    -1.34
     merits
    -1.32
     (§
    -1.31
    POSITIVE LOGITS
    Ģ
    3.60
    3.54
    <|outofrange|>
    3.54
    3.54
    <|outofrange|>
    3.54
    ↵
    3.54
    č↵
    3.54
    ↵
    3.54
    <|outofrange|>
    3.54
    <|outofrange|>
    3.54
    Activations Density 1.152%

    No Known Activations