© 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. 1-RES-SM
    11. 29365
    Prev
    Next
    INDEX
    Explanations

    references to solo performances or instances of solo work

    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
    156
    +0.21
    1.2%
    438
    +0.15
    0.9%
    282
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.21
    0.04
    156
    +0.15
    0.03
    271
    +0.12
    0.01
    Negative Logits
    rapeut
    -1.68
    woke
    -1.62
    rae
    -1.52
    rely
    -1.51
    illance
    -1.47
    roz
    -1.46
    rian
    -1.44
    ureus
    -1.43
    uca
    -1.41
     deteriorated
    -1.41
    POSITIVE LOGITS
    ¾
    2.52
    ĭ
    2.46
    Ĭ
    2.43
    ī
    2.40
    ¥
    2.37
    ¿
    2.36
    ¹
    2.34
    ł
    2.28
    £
    2.28
    ½
    2.25
    Activations Density 0.303%

    No Known Activations