© 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. 10675
    Prev
    Next
    INDEX
    Explanations

    data structures and parameters within structured data or coding contexts

    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
    169
    +0.13
    0.8%
    223
    +0.13
    0.8%
    393
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.13
    0.03
    175
    +0.13
    0.02
    374
    +0.13
    0.02
    Negative Logits
    ...](
    -1.74
    port
    -1.68
    ]."
    -1.65
    ports
    -1.64
     miles
    -1.54
    .")
    -1.54
    .]
    -1.53
    formatter
    -1.52
    stream
    -1.50
    rying
    -1.50
    POSITIVE LOGITS
    ľĵ
    2.78
    ĥ
    2.71
    ´
    2.68
    ĥ½
    2.64
    ħ
    2.62
    ¹
    2.58
    ĨĴ
    2.57
    ĸ´
    2.54
    °
    2.54
    IJ
    2.50
    Activations Density 0.261%

    No Known Activations