© 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. 1-RES-SM
    11. 26191
    Prev
    Next
    INDEX
    Explanations

    references to visual representations or images

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    368
    +0.16
    0.9%
    376
    +0.12
    0.6%
    115
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.16
    0.02
    72
    +0.12
    0.02
    485
    +0.11
    0.01
    Negative Logits
    =”
    -1.85
    atinum
    -1.51
    ī
    -1.51
    Ń
    -1.48
    =.
    -1.47
     sale
    -1.47
    NOTES
    -1.46
    chaft
    -1.46
    ricular
    -1.45
    ime
    -1.44
    POSITIVE LOGITS
    hin
    1.86
     prominently
    1.69
     respect
    1.64
    eking
    1.56
     sight
    1.55
     regard
    1.54
    ÅĦ
    1.52
    igh
    1.51
     glimps
    1.50
     evidence
    1.49
    Activations Density 0.072%

    No Known Activations