© 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. 4-RES-SM
    11. 14101
    Prev
    Next
    INDEX
    Explanations

    instances of the word "inf" and its variations, indicating a focus on information or statements related to health or 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    501
    +0.13
    0.7%
    209
    +0.12
    0.7%
    227
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.13
    0.02
    209
    +0.12
    0.02
    386
    +0.12
    0.01
    Negative Logits
    soever
    -1.74
    merce
    -1.60
    Simplify
    -1.53
    abouts
    -1.50
    ses
    -1.46
    cast
    -1.43
     reform
    -1.42
     alternatively
    -1.41
     County
    -1.41
     replacements
    -1.40
    POSITIVE LOGITS
    ³
    4.44
    Ĵ
    4.24
    ·¸
    4.24
    ª
    4.14
    §
    4.07
    Ĩ
    4.07
    Ļª
    3.92
    ĻĤ
    3.91
    ı
    3.88
    »
    3.86
    Activations Density 0.109%

    No Known Activations