© 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. 13249
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical descriptions or attributes of objects

    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
    78
    +0.13
    0.7%
    203
    +0.11
    0.7%
    240
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.13
    0.02
    477
    +0.11
    0.02
    387
    +0.11
    0.02
    Negative Logits
    lands
    -1.88
    gery
    -1.84
    iginally
    -1.65
    las
    -1.57
    liga
    -1.51
    EventListener
    -1.50
    lift
    -1.46
    leans
    -1.44
    ligt
    -1.42
    hei
    -1.40
    POSITIVE LOGITS
    Ħ
    3.78
    ³
    3.77
    ĨĴ
    3.67
    ¤
    3.58
    ĵ
    3.48
    ij
    3.45
    ¡
    3.41
    į
    3.35
    º
    3.34
    ¬
    3.33
    Activations Density 0.043%

    No Known Activations