© 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. 28099
    Prev
    Next
    INDEX
    Explanations

    the mention of the word "Bel" 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
    246
    +0.13
    0.7%
    391
    +0.11
    0.6%
    200
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.13
    0.01
    1
    +0.11
    0.01
    373
    +0.11
    0.01
    Negative Logits
    )">
    -1.49
    )}=\
    -1.46
    ème
    -1.45
    NEY
    -1.45
    :&
    -1.44
    \}}
    -1.42
    )}$$
    -1.39
     (@
    -1.37
     alumni
    -1.37
    )}.$$
    -1.36
    POSITIVE LOGITS
    bridge
    1.63
    nex
    1.51
    google
    1.49
    endar
    1.49
    gium
    1.47
    prove
    1.46
    gor
    1.44
    grass
    1.37
    quest
    1.36
    posts
    1.36
    Activations Density 0.041%

    No Known Activations