© 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. 4-RES-SM
    11. 10130
    Prev
    Next
    INDEX
    Explanations

    the phrase "free software" related to licensing

    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
    172
    +0.14
    0.9%
    78
    +0.12
    0.7%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.14
    0.02
    13
    +0.12
    0.01
    391
    +0.11
    0.01
    Negative Logits
    ingly
    -1.95
    ILY
    -1.79
    sworth
    -1.60
    ment
    -1.59
    perg
    -1.49
    merce
    -1.49
    los
    -1.49
    hey
    -1.47
    steine
    -1.47
    olson
    -1.46
    POSITIVE LOGITS
    ¥
    2.27
    ¹
    2.22
    ŀ
    2.21
    ħ
    2.21
    ¤
    2.21
    Ĵ
    2.19
    Ĩ
    2.17
    ·
    2.13
    ¸
    2.11
    Īĺ
    2.05
    Activations Density 0.018%

    No Known Activations