© 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. 2-RES-SM
    11. 31152
    Prev
    Next
    INDEX
    Explanations

    instances of stylesheet and script elements in HTML documents

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    494
    +0.10
    0.6%
    225
    +0.10
    0.5%
    173
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.10
    0.01
    173
    +0.10
    0.01
    433
    +0.10
    0.01
    Negative Logits
    ipes
    -1.85
    ently
    -1.82
    ennes
    -1.72
    ines
    -1.58
    inally
    -1.57
    omitempty
    -1.57
    upon
    -1.52
    ately
    -1.51
     endif
    -1.51
    ily
    -1.49
    POSITIVE LOGITS
    ¦
    1.54
     sleeve
    1.53
    rization
    1.50
    horn
    1.49
    ¸
    1.43
    rial
    1.40
    ERTY
    1.38
    ij
    1.38
    TING
    1.38
    sheet
    1.37
    Activations Density 0.085%

    No Known Activations