© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-MLP-SM
    11. 27865
    Prev
    Next
    INDEX
    Explanations

    repeated, structured elements in a document, particularly those indicating sections or items within a list

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    210
    +0.12
    0.6%
    115
    +0.11
    0.6%
    101
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.12
    0.10
    151
    +0.11
    0.09
    76
    +0.11
    0.10
    Negative Logits
    izumab
    -1.82
    ramento
    -1.66
    '));
    -1.59
    gio
    -1.56
    idd
    -1.48
    Ps
    -1.45
    isten
    -1.44
    googleapis
    -1.41
    idium
    -1.39
    rae
    -1.39
    POSITIVE LOGITS
     ending
    1.65
    iliar
    1.46
     toy
    1.45
     example
    1.44
     sculpture
    1.41
     sides
    1.40
    construct
    1.38
    ...)
    1.34
     foot
    1.34
    front
    1.33
    Activations Density 0.314%

    No Known Activations