© 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. 2-MLP-SM
    11. 23177
    Prev
    Next
    INDEX
    Explanations

    references to physical health and related conditions

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.14
    0.8%
    133
    +0.10
    0.6%
    286
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.14
    0.02
    446
    +0.10
    0.01
    448
    +0.10
    0.01
    Negative Logits
    /~
    -1.64
    ournal
    -1.44
    bro
    -1.42
    ($_
    -1.41
    /$
    -1.36
    />.
    -1.36
    etc
    -1.35
     sacrifices
    -1.34
    heer
    -1.34
    ftware
    -1.33
    POSITIVE LOGITS
     second
    1.44
    ched
    1.39
    URAL
    1.36
     closer
    1.34
    last
    1.34
     square
    1.33
    rified
    1.32
    ¯
    1.32
     north
    1.31
    IJ
    1.31
    Activations Density 0.113%

    No Known Activations