© 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. 14948
    Prev
    Next
    INDEX
    Explanations

    references to personal income and financial advice

    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
    307
    +0.17
    1.0%
    208
    +0.14
    0.8%
    390
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.17
    0.09
    58
    +0.14
    0.07
    24
    +0.13
    0.02
    Negative Logits
    Ĥ
    -3.96
    Į
    -3.94
    ·
    -3.91
    Ń
    -3.82
    £
    -3.79
    ¸
    -3.73
    °
    -3.71
    ĥ½
    -3.70
    »¿
    -3.69
    ´
    -3.68
    POSITIVE LOGITS
     HN
    4.01
     \-
    3.31
    \.
    2.70
     _
    2.49
     github
    2.14
     **[
    2.08
    ↵↵
    2.07
     :-)
    2.07
     *_
    2.07
     :)
    2.06
    Activations Density 1.005%

    No Known Activations