© 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. 29002
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ink" and related terms

    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
    108
    +0.13
    0.7%
    477
    +0.12
    0.7%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.13
    0.03
    256
    +0.12
    0.03
    488
    +0.12
    0.03
    Negative Logits
    §
    -2.07
    ³
    -1.96
    Īĺ
    -1.94
    ©
    -1.93
    Ĥ
    -1.84
    ķ
    -1.81
    Ĺ
    -1.78
    ¦
    -1.74
    ·
    -1.72
    Ń
    -1.69
    POSITIVE LOGITS
    manship
    1.99
    owski
    1.73
    elijk
    1.71
    oku
    1.67
    iewicz
    1.63
    rams
    1.61
    ovich
    1.55
    boards
    1.54
    lists
    1.51
    ermann
    1.49
    Activations Density 0.201%

    No Known Activations