© 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. 29722
    Prev
    Next
    INDEX
    Explanations

    terms related to ground or earth

    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
    164
    +0.20
    1.2%
    115
    +0.14
    0.8%
    389
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.20
    0.04
    389
    +0.14
    0.03
    115
    +0.12
    0.02
    Negative Logits
    Ĥ
    -2.47
    ¡
    -2.37
    ħ
    -2.34
    ¥
    -2.33
    ²
    -2.28
    ¾
    -2.20
    ĥ½
    -2.18
    ł
    -2.17
    Ĩ
    -2.16
    Ń
    -2.16
    POSITIVE LOGITS
    breaker
    2.19
    breaking
    2.13
    nuts
    2.04
    nut
    1.92
    woods
    1.83
    ball
    1.79
    hog
    1.78
    break
    1.76
    itat
    1.66
    liner
    1.62
    Activations Density 0.114%

    No Known Activations