© 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. 24764
    Prev
    Next
    INDEX
    Explanations

    sentences that make definitive statements or conclusions

    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
    249
    +0.16
    0.9%
    84
    +0.14
    0.8%
    358
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.04
    271
    +0.14
    0.02
    156
    +0.14
    0.02
    Negative Logits
    Ľ
    -2.58
    ĺ
    -2.24
    ı
    -2.17
    Īĺ
    -2.11
    ĥ
    -2.00
    Ĥ¬
    -1.98
    ²
    -1.97
    Ļ
    -1.97
    İ
    -1.97
    ħ
    -1.95
    POSITIVE LOGITS
    izumab
    1.56
    ="../../../
    1.55
    ın
    1.50
    lu
    1.49
    libs
    1.48
    rv
    1.48
     prove
    1.46
    stic
    1.42
    lessness
    1.37
     preserve
    1.36
    Activations Density 0.006%

    No Known Activations