© 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. 14465
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and brain tissue

    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
    21
    +0.23
    1.4%
    397
    +0.19
    1.1%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.23
    0.10
    21
    +0.19
    0.07
    78
    +0.11
    -0.02
    Negative Logits
    itated
    -1.39
    ient
    -1.32
    itating
    -1.31
    itate
    -1.30
    tern
    -1.29
    quare
    -1.28
     rounding
    -1.24
     Binary
    -1.24
     ERROR
    -1.22
     ceil
    -1.22
    POSITIVE LOGITS
     immunotherapy
    1.93
     buses
    1.75
    Walker
    1.73
     Walker
    1.72
     drive
    1.69
     mosquitoes
    1.65
     CAR
    1.64
     Martinez
    1.60
     Kurd
    1.60
     vaccine
    1.60
    Activations Density 2.005%

    No Known Activations