Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28975
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions or diseases

    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
    350
    +0.15
    0.9%
    92
    +0.14
    0.8%
    334
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.15
    0.06
    391
    +0.14
    0.05
    92
    +0.13
    0.06
    Negative Logits
    ieurs
    -1.91
     thereof
    -1.83
    pshire
    -1.51
    ½
    -1.47
    Ī
    -1.44
    pecially
    -1.43
    lections
    -1.43
    »¿
    -1.41
    .).
    -1.39
    ı
    -1.37
    POSITIVE LOGITS
     falciparum
    1.56
     SARS
    1.47
    awn
    1.40
    iels
    1.40
    apine
    1.38
     killers
    1.37
    inux
    1.36
    umab
    1.35
    keit
    1.35
    thood
    1.34
    Activations Density 0.825%

    No Known Activations