© 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. MLP Post
    9. 0-MLP-SM
    11. 30404
    Prev
    Next
    INDEX
    Explanations

    specific sequences of characters that match the term "abc"

    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
    177
    +0.14
    0.8%
    251
    +0.12
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.14
    0.01
    111
    +0.12
    0.01
    215
    +0.11
    0.01
    Negative Logits
     ago
    -2.04
    ?"
    -1.59
    ĨĴ
    -1.56
    ?'
    -1.49
    ľ
    -1.48
    ı
    -1.48
    ONS
    -1.47
    abouts
    -1.44
    '?"
    -1.44
    ?)
    -1.43
    POSITIVE LOGITS
    func
    1.79
    dom
    1.75
    band
    1.71
    enstein
    1.67
    prep
    1.54
    nex
    1.51
    stone
    1.50
    bands
    1.49
    bench
    1.49
    erals
    1.46
    Activations Density 0.407%

    No Known Activations