© 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. 29823
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Fox."

    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
    369
    +0.22
    1.3%
    349
    +0.14
    0.8%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.22
    0.02
    416
    +0.14
    0.02
    412
    +0.14
    0.02
    Negative Logits
    ľ
    -2.18
    IJ
    -1.97
    ĺ
    -1.82
    ľĵ
    -1.80
    ĥ½
    -1.79
    Ļ
    -1.75
    ĨĴ
    -1.73
     '</
    -1.70
    £
    -1.70
    §
    -1.63
    POSITIVE LOGITS
    boro
    2.27
    conn
    1.99
    woods
    1.84
    bank
    1.79
    craft
    1.77
    hill
    1.73
    worthy
    1.71
    ygen
    1.71
    chet
    1.69
    films
    1.65
    Activations Density 0.014%

    No Known Activations