© 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. 26474
    Prev
    Next
    INDEX
    Explanations

    the word "bank" in various contexts

    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
    411
    +0.14
    0.8%
    217
    +0.11
    0.7%
    252
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.14
    0.01
    189
    +0.11
    0.01
    162
    +0.10
    0.01
    Negative Logits
    Ĥ
    -2.38
    ĥ½
    -2.37
    §
    -2.15
    Ĥ¬
    -2.03
    Ĩ
    -1.90
    ľ
    -1.88
    ¶
    -1.86
    ¥
    -1.83
    Ń
    -1.80
    ¿½
    -1.79
    POSITIVE LOGITS
    ruptcy
    2.83
    notes
    1.92
    able
    1.84
    ÅĽci
    1.83
    yard
    1.82
    rupt
    1.81
    elines
    1.81
    ers
    1.79
    etable
    1.79
    ed
    1.77
    Activations Density 0.010%

    No Known Activations