© 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. 13951
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and elements in a document

    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
    78
    +0.18
    1.0%
    315
    +0.14
    0.8%
    341
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.18
    0.06
    325
    +0.14
    0.06
    341
    +0.11
    0.04
    Negative Logits
    forth
    -1.72
     herself
    -1.52
    optera
    -1.50
    INE
    -1.49
    ,’
    -1.49
    cloth
    -1.48
     ‘
    -1.48
    inux
    -1.45
     ende
    -1.42
     oneself
    -1.39
    POSITIVE LOGITS
     />
    3.50
     /><
    2.71
    ></
    2.62
     /></
    2.57
    />
    2.56
    >&
    2.52
     BGCOLOR
    2.50
    į
    2.46
     xmlns
    2.44
    ><
    2.43
    Activations Density 0.182%

    No Known Activations