© 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. 9467
    Prev
    Next
    INDEX
    Explanations

    discussions regarding financial support and funding for social programs and communities

    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
    +0.39
    2.5%
    306
    +0.26
    1.7%
    466
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.39
    0.16
    306
    +0.26
    0.12
    307
    +0.12
    0.17
    Negative Logits
    acters
    -1.55
    liness
    -1.46
    **).
    -1.40
    ctomy
    -1.39
     picture
    -1.39
    ↵³³
    -1.33
     constants
    -1.31
    keit
    -1.29
    noreply
    -1.29
     etc
    -1.27
    POSITIVE LOGITS
    ĥ½
    3.82
    »¿
    3.69
    Ļª
    3.68
    ĸ´
    3.67
    ¿½
    3.55
    §
    3.43
    Ł
    3.42
    ĻĤ
    3.37
    ↵
    3.32
    3.32
    Activations Density 1.931%

    No Known Activations