© 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. 27837
    Prev
    Next
    INDEX
    Explanations

    numerical lists or sequences related to legal or procedural requirements

    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
    419
    +0.14
    0.8%
    499
    +0.12
    0.7%
    395
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.14
    0.02
    128
    +0.12
    0.02
    136
    +0.12
    -0.00
    Negative Logits
    Ļª
    -2.34
    ¸
    -2.08
    ¿½
    -2.04
    ¨
    -2.04
    ¥
    -1.93
    »
    -1.93
    IJ
    -1.89
    §
    -1.87
    »¿
    -1.86
    Ļ
    -1.84
    POSITIVE LOGITS
     nothing
    1.52
     insofar
    1.50
    iberal
    1.41
    rely
    1.41
    opically
    1.39
    nexpected
    1.39
     none
    1.35
     denying
    1.34
     apart
    1.34
     occasions
    1.30
    Activations Density 0.196%

    No Known Activations