© 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. 26276
    Prev
    Next
    INDEX
    Explanations

    the presence of informative introductions or summaries in documents

    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
    43
    +0.14
    0.8%
    162
    +0.12
    0.7%
    108
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.14
    0.01
    23
    +0.12
    0.01
    129
    +0.12
    0.00
    Negative Logits
    ģ
    -3.52
    ¿½
    -3.51
    Ł
    -3.48
    Ĥ¬
    -3.47
    ħ
    -3.46
    ľĵ
    -3.40
    ²
    -3.35
    IJ
    -3.33
    ŀ
    -3.27
    °
    -3.13
    POSITIVE LOGITS
     -->
    1.49
     fine
    1.47
     decide
    1.44
     huh
    1.41
     behaving
    1.39
     ">
    1.37
     backdrop
    1.37
     standing
    1.35
    oxacin
    1.35
    dry
    1.33
    Activations Density 0.003%

    No Known Activations