© 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. 26425
    Prev
    Next
    INDEX
    Explanations

    references to a specific character or franchise, particularly related to "Batman."

    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
    +0.18
    1.0%
    376
    +0.18
    1.0%
    44
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.18
    0.01
    265
    +0.18
    0.01
    465
    +0.13
    0.01
    Negative Logits
    Ń
    -3.90
    ĥ½
    -3.68
    ĸ´
    -3.66
    ĥ
    -3.66
    ´
    -3.59
    §
    -3.58
    ·¸
    -3.52
    »¿
    -3.50
    Ļª
    -3.50
    Ĩ
    -3.44
    POSITIVE LOGITS
    shots
    1.83
    iste
    1.69
    isti
    1.63
    ist
    1.62
    ingly
    1.49
    ism
    1.48
    ista
    1.47
    shot
    1.43
    que
    1.42
    ically
    1.41
    Activations Density 0.009%

    No Known Activations