© 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. 27808
    Prev
    Next
    INDEX
    Explanations

    section headers or formatting indicators in documents

    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
    115
    +0.14
    0.8%
    129
    +0.13
    0.7%
    250
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.14
    0.01
    261
    +0.13
    0.01
    390
    +0.11
    0.01
    Negative Logits
    .^[@
    -1.50
    )^[@
    -1.49
    chell
    -1.48
     winner
    -1.45
    neb
    -1.44
    ^[@
    -1.39
    zin
    -1.39
     CBC
    -1.38
     "/
    -1.36
     ago
    -1.35
    POSITIVE LOGITS
    ĻĤ
    1.59
    udes
    1.52
    iberal
    1.48
    ington
    1.47
     regards
    1.45
    andals
    1.45
    gate
    1.43
    notes
    1.41
    hora
    1.39
    nabla
    1.39
    Activations Density 0.010%

    No Known Activations