© 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 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. 12590
    Prev
    Next
    INDEX
    Explanations

    specific measurements and scientific parameters related to biological experiments

    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
    32
    +0.13
    0.7%
    293
    +0.12
    0.7%
    198
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.13
    0.04
    321
    +0.12
    0.03
    85
    +0.12
    0.04
    Negative Logits
     vulnerabilities
    -1.68
     inherited
    -1.68
     geneal
    -1.64
    unnumbered
    -1.61
     anomalies
    -1.56
     associations
    -1.55
     syndromes
    -1.51
     epidemiology
    -1.48
     faults
    -1.47
     crashes
    -1.46
    POSITIVE LOGITS
     solution
    2.51
     distilled
    2.46
     saline
    2.30
     NaCl
    2.30
     pH
    2.28
     overnight
    2.25
     supernatant
    2.22
     dilution
    2.19
    solution
    2.15
     mixture
    2.14
    Activations Density 0.465%

    No Known Activations