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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 12328
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to heart health and cardiovascular 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
    444
    +0.13
    0.7%
    468
    +0.12
    0.7%
    373
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    0.03
    468
    +0.12
    0.02
    28
    +0.11
    0.01
    Negative Logits
     Redistributions
    -1.75
    xtures
    -1.67
    ictions
    -1.61
    ceq
    -1.58
    ftware
    -1.49
    isible
    -1.48
    OUS
    -1.44
    ppo
    -1.43
    "}](#
    -1.42
    heet
    -1.42
    POSITIVE LOGITS
    felt
    2.28
    worm
    2.24
     valves
    2.23
     valve
    2.21
    beat
    2.19
     failure
    2.08
    burn
    1.94
     rate
    1.93
     beat
    1.88
    stroke
    1.84
    Activations Density 0.064%

    No Known Activations