© 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. 1-RES-SM
    11. 24969
    Prev
    Next
    INDEX
    Explanations

    terms related to skin abnormalities or 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.27
    1.7%
    247
    +0.13
    0.8%
    376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.27
    0.01
    156
    +0.13
    0.01
    184
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.09
    »¿
    -2.08
     yours
    -2.00
     ↵
    -1.99
     ↵
    -1.99
    ↵
    -1.99
    -1.99
    ↵
    -1.99
    -1.99
     ↵
    -1.99
    POSITIVE LOGITS
    arial
    1.76
    ary
    1.70
    al
    1.63
    \[[@
    1.63
    CTX
    1.53
    PV
    1.50
     duration
    1.48
    stre
    1.47
    oid
    1.46
     lesion
    1.44
    Activations Density 0.054%

    No Known Activations