© 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. 29522
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "P" as standalone characters

    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
    369
    +0.25
    1.5%
    502
    +0.13
    0.8%
    191
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.25
    0.04
    486
    +0.13
    0.04
    351
    +0.12
    0.04
    Negative Logits
    ¼
    -3.62
    º
    -2.75
    ĥ½
    -2.64
    °
    -2.62
    Īĺ
    -2.61
    »
    -2.53
    ·¸
    -2.48
    ĸ´
    -2.45
    ģ
    -2.38
    ·
    -2.36
    POSITIVE LOGITS
    IPE
    1.81
    GF
    1.80
    inte
    1.73
    HEL
    1.72
    ZA
    1.68
    WD
    1.65
    GS
    1.64
    GA
    1.61
     Films
    1.61
    ilot
    1.56
    Activations Density 0.120%

    No Known Activations