© 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. 25817
    Prev
    Next
    INDEX
    Explanations

    emphasized concepts of significance or importance in various contexts

    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
    237
    +0.16
    0.9%
    376
    +0.12
    0.7%
    489
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.16
    0.05
    489
    +0.12
    0.03
    438
    +0.12
    0.03
    Negative Logits
    kel
    -1.54
    itzer
    -1.46
    ativo
    -1.43
    bage
    -1.40
     FALSE
    -1.39
    TEST
    -1.39
    rives
    -1.38
    TING
    -1.36
    zen
    -1.34
    INO
    -1.31
    POSITIVE LOGITS
    ĸ
    2.30
    º
    2.21
    ĵ
    2.10
    ¢
    2.08
    ¦
    2.06
    ŀ
    1.98
    ¨
    1.97
    £
    1.96
    ľĵ
    1.93
    ł
    1.93
    Activations Density 0.043%

    No Known Activations