© 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. 24863
    Prev
    Next
    INDEX
    Explanations

    themes related to growth and necessity

    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
    170
    +0.12
    0.7%
    70
    +0.11
    0.6%
    265
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.12
    0.07
    62
    +0.11
    0.05
    397
    +0.11
    0.04
    Negative Logits
    ·¸
    -3.40
    ľĵ
    -3.37
    ĻĤ
    -3.35
    »¿
    -3.33
    Īĺ
    -3.23
    ²
    -3.16
    ¿½
    -3.16
    ľ
    -3.12
    ¡
    -2.96
    Į
    -2.95
    POSITIVE LOGITS
    ème
    1.75
     stage
    1.73
     of
    1.68
     regime
    1.67
     genre
    1.59
    lichen
    1.54
    ec
    1.49
    way
    1.48
     era
    1.46
    ive
    1.45
    Activations Density 1.205%

    No Known Activations