© 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. 25629
    Prev
    Next
    INDEX
    Explanations

    HTML link tags 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/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
    256
    +0.13
    0.7%
    260
    +0.13
    0.7%
    44
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.03
    252
    +0.13
    0.02
    21
    +0.12
    0.02
    Negative Logits
    ²
    -2.48
    Ļ
    -2.21
    ł
    -2.15
    ¨
    -2.09
    Ł
    -2.04
    ĺ
    -1.99
    ľ
    -1.90
    §
    -1.88
    Īĺ
    -1.83
    »¿
    -1.80
    POSITIVE LOGITS
    age
    2.31
    horn
    1.94
    forge
    1.90
    ://
    1.79
    #:
    1.78
    wort
    1.75
    ="_
    1.66
    marks
    1.66
    pad
    1.62
    amycin
    1.58
    Activations Density 0.048%

    No Known Activations