© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    references to health organizations and institutions

    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
    +0.13
    0.7%
    179
    +0.12
    0.7%
    130
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.13
    0.09
    242
    +0.12
    0.08
    168
    +0.11
    0.08
    Negative Logits
    ↵
    -5.32
    -5.32
    -5.32
    ↵
    -5.32
    ↵
    -5.32
     ↵
    -5.32
    <|outofrange|>
    -5.32
    ↵
    -5.32
    <|outofrange|>
    -5.32
    <|outofrange|>
    -5.32
    POSITIVE LOGITS
     guidelines
    2.39
     website
    2.29
     Guidelines
    2.23
     approval
    2.19
     Annual
    2.12
    wide
    2.09
     member
    2.07
     recommends
    2.06
     annual
    2.03
     agrees
    1.99
    Activations Density 0.892%

    No Known Activations