© 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. 28049
    Prev
    Next
    INDEX
    Explanations

    references to upcoming events or future plans

    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
    30
    +0.14
    0.8%
    11
    +0.11
    0.6%
    142
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.14
    0.05
    11
    +0.11
    0.04
    374
    +0.10
    0.04
    Negative Logits
    Ļª
    -2.55
    »¿
    -2.25
    ĩ
    -2.18
    inity
    -1.90
    ĻĤ
    -1.85
    ®
    -1.78
    §
    -1.76
    ¢
    -1.75
     Pradesh
    -1.71
    Ī
    -1.71
    POSITIVE LOGITS
     competitor
    1.64
     generations
    1.63
    ellt
    1.58
     mate
    1.56
     wave
    1.50
    chter
    1.50
     foe
    1.49
     steps
    1.48
     hur
    1.47
     mates
    1.44
    Activations Density 0.134%

    No Known Activations