© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28599
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and treatments, particularly related to cardiac health and organ transplantation

    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
    369
    +0.18
    1.1%
    156
    +0.15
    0.8%
    350
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.18
    0.06
    350
    +0.15
    0.04
    443
    +0.13
    0.03
    Negative Logits
     blame
    -1.80
    JUST
    -1.71
     attention
    -1.55
    dala
    -1.54
    ··
    -1.49
    ided
    -1.48
    andum
    -1.44
     endless
    -1.43
    veh
    -1.43
     wonder
    -1.43
    POSITIVE LOGITS
    igan
    2.07
    iff
    2.03
    oon
    1.96
    ioni
    1.83
    wick
    1.73
    ains
    1.72
    ovic
    1.69
    ilian
    1.67
    ucci
    1.67
    upt
    1.65
    Activations Density 0.332%

    No Known Activations