© 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. 30750
    Prev
    Next
    INDEX
    Explanations

    instances of the word "well" used to denote quality or condition

    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
    258
    +0.11
    0.6%
    0
    +0.10
    0.5%
    66
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.11
    0.05
    0
    +0.10
    0.05
    20
    +0.10
    0.05
    Negative Logits
     scene
    -1.55
    ursuant
    -1.42
     whole
    -1.40
     session
    -1.39
     needed
    -1.37
     leak
    -1.35
     entire
    -1.33
     console
    -1.31
     suite
    -1.31
     creation
    -1.30
    POSITIVE LOGITS
    bred
    1.56
    beck
    1.56
    VB
    1.47
    haus
    1.41
    endor
    1.40
    standing
    1.37
    heit
    1.34
    lied
    1.31
    pson
    1.30
    chaft
    1.29
    Activations Density 0.117%

    No Known Activations