© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25253
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or brackets in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    332
    +0.11
    0.6%
    43
    +0.11
    0.6%
    89
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.11
    0.07
    415
    +0.11
    0.05
    249
    +0.11
    0.06
    Negative Logits
    unes
    -1.76
    ollen
    -1.45
    .[]{
    -1.45
    utton
    -1.44
    fax
    -1.38
    amente
    -1.38
     dunge
    -1.37
    rapeut
    -1.32
     ell
    -1.28
    ľĵ
    -1.27
    POSITIVE LOGITS
    acity
    1.76
    eless
    1.59
    <<
    1.52
    "}](
    1.48
    ility
    1.48
    +^
    1.47
    makers
    1.45
    bling
    1.38
    false
    1.35
    etime
    1.33
    Activations Density 0.273%

    No Known Activations