© 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. 24528
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss various effects or impacts related to specific topics

    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
    110
    +0.13
    0.7%
    187
    +0.11
    0.6%
    471
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.13
    0.02
    110
    +0.11
    0.02
    187
    +0.10
    0.02
    Negative Logits
    ¸
    -2.54
    ĸ´
    -2.28
    »¿
    -2.26
    ¼
    -2.20
    ¿½
    -2.19
    ±
    -2.07
    ·¸
    -2.06
    »
    -2.06
    ´
    -2.00
    ĨĴ
    -1.97
    POSITIVE LOGITS
    ivation
    2.04
    uating
    2.04
    uation
    2.02
    uate
    1.95
    ivity
    1.88
    uated
    1.88
    ual
    1.83
    iveness
    1.82
    ives
    1.80
     rate
    1.72
    Activations Density 0.040%

    No Known Activations