© 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. 2-RES-SM
    11. 12854
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly statistics and prevalence related to medical 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/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
    +0.16
    0.9%
    374
    +0.14
    0.8%
    33
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.16
    0.02
    329
    +0.14
    0.01
    81
    +0.13
    0.01
    Negative Logits
    ?)
    -1.65
     containing
    -1.58
    ?).
    -1.56
     masses
    -1.48
    inas
    -1.45
     balls
    -1.44
    ines
    -1.44
     weights
    -1.43
    ?",
    -1.40
    ?”
    -1.38
    POSITIVE LOGITS
    reatment
    1.58
    ude
    1.57
    ½
    1.43
    udeau
    1.37
    APTER
    1.32
    ajor
    1.29
    /
    1.28
    ek
    1.22
     COURT
    1.21
    orsch
    1.20
    Activations Density 0.020%

    No Known Activations