© 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 EvalsExportsAPI 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. 11112
    Prev
    Next
    INDEX
    Explanations

    instructions related to physical exercises

    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
    153
    +0.18
    1.0%
    210
    +0.15
    0.9%
    25
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.18
    0.18
    343
    +0.15
    0.10
    210
    +0.14
    -0.02
    Negative Logits
     cities
    -1.57
     communities
    -1.53
     publicly
    -1.52
     Commun
    -1.47
     Cities
    -1.47
     xen
    -1.46
     community
    -1.45
    ocarcin
    -1.45
    biz
    -1.44
    ocaust
    -1.43
    POSITIVE LOGITS
    »¿
    2.82
    »
    2.82
    ¬
    2.71
    ³
    2.70
    Īĺ
    2.65
    Ľ
    2.59
    ¯
    2.58
    ł
    2.58
    IJ
    2.56
    ·
    2.55
    Activations Density 4.067%

    No Known Activations