© 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. 2-RES-SM
    11. 10542
    Prev
    Next
    INDEX
    Explanations

    references to personal and collective struggles and achievements

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    198
    +0.15
    0.8%
    465
    +0.14
    0.8%
    421
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.15
    0.14
    246
    +0.14
    0.13
    292
    +0.14
    0.10
    Negative Logits
    Īĺ
    -3.01
    º
    -2.94
    Ĥ¬
    -2.91
    ¢
    -2.78
    ĥ
    -2.68
    Ģ
    -2.63
    Ĺ
    -2.62
    ĭ
    -2.48
    ª
    -2.43
    ĻĤ
    -2.39
    POSITIVE LOGITS
     reign
    1.43
    ELD
    1.35
     arrived
    1.33
     notation
    1.32
     COURT
    1.29
     reach
    1.29
     came
    1.28
    rsquo
    1.28
     Korean
    1.26
    ordo
    1.25
    Activations Density 2.827%

    No Known Activations