© 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. 25050
    Prev
    Next
    INDEX
    Explanations

    mentions of authors and their contributions

    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
    111
    +0.14
    0.8%
    168
    +0.13
    0.7%
    443
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.14
    0.01
    71
    +0.13
    0.01
    157
    +0.13
    0.01
    Negative Logits
    ```
    -1.44
    mining
    -1.44
     Circuit
    -1.40
    º
    -1.36
    ey
    -1.34
    aster
    -1.31
    ADVERTISEMENT
    -1.31
    correct
    -1.30
    %(
    -1.28
    break
    -1.28
    POSITIVE LOGITS
    eman
    1.59
    man
    1.52
    ista
    1.47
    terday
    1.41
    mates
    1.40
     talk
    1.37
    wers
    1.37
     memb
    1.35
    ól
    1.34
    hael
    1.33
    Activations Density 0.061%

    No Known Activations