© 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. 28586
    Prev
    Next
    INDEX
    Explanations

    topics related to healthcare and medical conditions

    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
    156
    +0.19
    1.1%
    15
    +0.13
    0.7%
    266
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    234
    +0.19
    0.09
    15
    +0.13
    0.09
    271
    +0.12
    -0.02
    Negative Logits
    Ľ
    -2.77
    §
    -2.68
    ¾
    -2.65
    Ļ
    -2.65
    ļ
    -2.60
    -2.57
    ↵↵↵
    -2.57
    ↵
    -2.57
     ↵
    -2.57
    ↵
    -2.57
    POSITIVE LOGITS
     ([@
    1.82
    ality
    1.71
    iast
    1.64
    [^
    1.52
    icz
    1.52
    onuclear
    1.51
    argin
    1.50
    ortic
    1.49
    ian
    1.49
    cript
    1.48
    Activations Density 1.354%

    No Known Activations