© 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. 24785
    Prev
    Next
    INDEX
    Explanations

    attributes related to HTML elements and tags

    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
    427
    +0.12
    0.7%
    218
    +0.12
    0.7%
    249
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.02
    184
    +0.12
    0.01
    461
    +0.11
    0.03
    Negative Logits
    »¿
    -1.79
    à°¿
    -1.75
    (/
    -1.72
    áĢ¯
    -1.57
     feat
    -1.55
    áĢ¸
    -1.53
     thereof
    -1.48
    ently
    -1.47
    áĢº
    -1.46
    ↵ ↵
    -1.39
    POSITIVE LOGITS
    "}](#
    2.13
    ]{.
    1.93
    ans
    1.71
    ms
    1.69
    ns
    1.51
    external
    1.51
    ocrates
    1.50
    "}](
    1.50
    pre
    1.45
    compare
    1.45
    Activations Density 0.154%

    No Known Activations