© 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. 24432
    Prev
    Next
    INDEX
    Explanations

    language related to permissions and 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/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
    347
    +0.13
    0.7%
    87
    +0.12
    0.7%
    211
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.13
    0.03
    211
    +0.12
    0.02
    202
    +0.11
    0.03
    Negative Logits
    ¢
    -3.98
    ®
    -3.70
    ļ
    -3.63
    §
    -3.58
    ¡
    -3.47
    ¾
    -3.36
    ±
    -3.30
    ¦
    -3.28
    IJ
    -3.25
    Ĺ
    -3.23
    POSITIVE LOGITS
     coh
    1.73
    ARRANT
    1.71
     polynomial
    1.58
     Redistributions
    1.54
    ributions
    1.47
    ospor
    1.44
     polynomials
    1.44
     MERCHANTABILITY
    1.43
     WARRANTY
    1.43
     remission
    1.41
    Activations Density 0.163%

    No Known Activations