© 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. 25636
    Prev
    Next
    INDEX
    Explanations

    verbs related to expulsion or removal

    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
    215
    +0.13
    0.7%
    25
    +0.12
    0.7%
    95
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    215
    +0.13
    0.02
    25
    +0.12
    0.02
    95
    +0.12
    0.01
    Negative Logits
    Į
    -2.19
    ĻĤ
    -2.01
    ľĵ
    -1.99
    Ļª
    -1.98
    ĸ´
    -1.94
    Ĺ
    -1.87
     behalf
    -1.80
    ĨĴ
    -1.79
    ĵ
    -1.76
    ¼
    -1.74
    POSITIVE LOGITS
    iry
    2.03
    atory
    1.82
    ository
    1.76
    ansion
    1.69
    ulsion
    1.66
    onential
    1.64
    onent
    1.58
    ressive
    1.54
    -[
    1.51
    iens
    1.51
    Activations Density 0.047%

    No Known Activations