© 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. 14710
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions

    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
    21
    +0.16
    0.9%
    258
    +0.13
    0.7%
    461
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.16
    0.03
    258
    +0.13
    0.04
    58
    +0.13
    0.04
    Negative Logits
    ¢
    -2.26
    ¿½
    -2.25
    ĵ
    -2.19
    ľ
    -2.06
    ľĵ
    -2.02
    Ģ
    -2.00
    ¶
    -1.97
    ĸ
    -1.94
    ¾
    -1.93
    )</
    -1.92
    POSITIVE LOGITS
     Denote
    2.89
     Then
    2.68
     Assume
    2.67
     Suppose
    2.41
     Define
    2.35
     Mathemat
    2.23
     Assuming
    2.13
     Consider
    2.13
     Let
    2.10
     Theorem
    2.10
    Activations Density 0.118%

    No Known Activations