© 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. 9669
    Prev
    Next
    INDEX
    Explanations

    references to public licenses, particularly the GNU General Public License

    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
    197
    +0.13
    0.8%
    34
    +0.12
    0.7%
    371
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.13
    0.02
    34
    +0.12
    0.02
    202
    +0.11
    0.01
    Negative Logits
    naire
    -1.55
    alone
    -1.46
    ÅĽ
    -1.45
    nae
    -1.39
    ctin
    -1.39
    hti
    -1.33
    dess
    -1.32
     towards
    -1.30
    noreply
    -1.25
    ainen
    -1.25
    POSITIVE LOGITS
    иб
    1.99
    еÑĩ
    1.61
    наÑĩ
    1.59
     existence
    1.51
    Ñij
    1.51
    екÑĤ
    1.50
    енÑĮ
    1.49
    ÑĥÑĢ
    1.49
    еÑĢ
    1.47
    Ñĥж
    1.46
    Activations Density 0.031%

    No Known Activations