© 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. 4-RES-SM
    11. 11416
    Prev
    Next
    INDEX
    Explanations

    components related to legal or procedural contexts

    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
    348
    +0.28
    1.7%
    78
    +0.24
    1.5%
    306
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.28
    -0.02
    348
    +0.24
    0.06
    255
    +0.15
    -0.04
    Negative Logits
    ubicin
    -1.60
     asleep
    -1.51
    yet
    -1.42
    ment
    -1.38
    .(
    -1.37
    eous
    -1.34
    xico
    -1.33
    aceuticals
    -1.32
    nament
    -1.31
    abetes
    -1.30
    POSITIVE LOGITS
                ↵
    8.44
    ↵
    8.44
    ↵
    8.44
     ↵
    8.44
    <|outofrange|>
    8.44
    8.44
    8.44
    ↵
    8.44
    8.44
    <|outofrange|>
    8.44
    Activations Density 1.735%

    No Known Activations