© 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. 10408
    Prev
    Next
    INDEX
    Explanations

    HTML attributes in a document

    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
    271
    +0.16
    0.9%
    436
    +0.14
    0.8%
    176
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.16
    0.02
    325
    +0.14
    0.03
    210
    +0.11
    0.01
    Negative Logits
    apters
    -1.92
    iates
    -1.75
    asures
    -1.66
    engers
    -1.64
    iation
    -1.63
    opause
    -1.60
    iale
    -1.58
    iento
    -1.55
    hering
    -1.51
    ameth
    -1.50
    POSITIVE LOGITS
    ¿
    4.01
    IJ
    3.81
    ¢
    3.76
    ¹
    3.76
    °
    3.68
    ¡
    3.61
    ł
    3.61
    ¼
    3.56
    ¸
    3.55
    Ĵ
    3.52
    Activations Density 0.101%

    No Known Activations