© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28738
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or health conditions and their diagnostics

    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
    89
    +0.14
    0.8%
    159
    +0.14
    0.8%
    334
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.14
    0.02
    334
    +0.14
    0.02
    89
    +0.12
    0.01
    Negative Logits
     surprise
    -1.60
     promise
    -1.59
    RNAs
    -1.50
    edited
    -1.42
     lineback
    -1.41
     yet
    -1.40
     saber
    -1.39
    ships
    -1.39
    Īĺ
    -1.37
     dice
    -1.37
    POSITIVE LOGITS
    ialysis
    1.78
    ière
    1.70
    artment
    1.67
    ervation
    1.60
    amin
    1.56
    der
    1.56
    ikt
    1.50
     Springs
    1.48
    shire
    1.48
    hurst
    1.46
    Activations Density 0.111%

    No Known Activations