© 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. 24557
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or geographical terms

    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
    404
    +0.15
    0.8%
    410
    +0.14
    0.8%
    369
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.03
    404
    +0.14
    0.03
    191
    +0.13
    0.02
    Negative Logits
    bbe
    -1.81
    áĢº
    -1.69
    teenth
    -1.59
    tain
    -1.59
    iator
    -1.52
    iates
    -1.49
    àµį
    -1.49
    efore
    -1.49
    ieur
    -1.47
    grades
    -1.47
    POSITIVE LOGITS
    istics
    1.75
    ungs
    1.59
    asm
    1.58
    owitz
    1.55
    án
    1.55
    resis
    1.50
    ume
    1.47
    une
    1.46
    elled
    1.45
    arts
    1.44
    Activations Density 0.156%

    No Known Activations