© 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. 25192
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that indicate a basis or foundation for statements or conclusions

    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
    365
    +0.14
    0.8%
    29
    +0.12
    0.7%
    417
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.14
    0.04
    29
    +0.12
    0.03
    463
    +0.11
    0.03
    Negative Logits
    "`
    -1.69
    )](#
    -1.55
    *](#
    -1.47
    ful
    -1.44
    aceae
    -1.42
    worth
    -1.41
    >`
    -1.39
    Ļª
    -1.38
    joy
    -1.38
    hy
    -1.38
    POSITIVE LOGITS
    eterm
    1.79
    ties
    1.62
    emann
    1.60
    going
    1.58
    inese
    1.57
    emente
    1.53
    outing
    1.52
    lining
    1.50
    ARM
    1.45
    ivat
    1.43
    Activations Density 0.091%

    No Known Activations