© 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. 2-RES-SM
    11. 27335
    Prev
    Next
    INDEX
    Explanations

    terms related to physical health and therapy

    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
    17
    +0.18
    1.1%
    271
    +0.18
    1.0%
    186
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.18
    -0.01
    93
    +0.18
    0.08
    186
    +0.13
    0.03
    Negative Logits
    ¯
    -4.50
    °
    -4.33
    Ĥ¬
    -4.32
    Īĺ
    -4.23
    ¶
    -4.14
    ı
    -4.13
    ¿
    -4.12
    Ķ
    -4.11
    ¸
    -4.10
    ķ
    -4.09
    POSITIVE LOGITS
    âĢ¦]
    1.59
    mapsto
    1.49
     through
    1.49
     cannot
    1.47
    èĢĮ
    1.42
    tern
    1.40
    MAX
    1.40
     ...
    1.37
    space
    1.37
    igraphy
    1.37
    Activations Density 1.250%

    No Known Activations