© 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. 14279
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "lin" or variations of it in different contexts

    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
    480
    +0.14
    0.7%
    437
    +0.13
    0.7%
    71
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.14
    0.04
    59
    +0.13
    0.03
    98
    +0.13
    0.01
    Negative Logits
     respect
    -1.78
     seriousness
    -1.50
    eer
    -1.48
     picture
    -1.47
     venue
    -1.45
     presence
    -1.43
     help
    -1.42
     photo
    -1.40
     preceding
    -1.40
    iliar
    -1.39
    POSITIVE LOGITS
    ³
    2.22
    nea
    2.08
    Ħ
    2.07
    Ĵ
    2.04
    ª
    2.03
    nae
    1.97
    ¾
    1.96
    q
    1.95
    us
    1.92
    º
    1.86
    Activations Density 0.231%

    No Known Activations