© 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. 26592
    Prev
    Next
    INDEX
    Explanations

    the mention of specific extremist groups

    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
    +0.20
    1.2%
    376
    +0.14
    0.8%
    307
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.20
    0.01
    94
    +0.14
    0.01
    281
    +0.13
    0.01
    Negative Logits
    ľĵ
    -1.82
     late
    -1.60
     her
    -1.56
    Ļª
    -1.56
    teenth
    -1.53
    "?"
    -1.51
     former
    -1.45
    orkshire
    -1.41
    usterity
    -1.40
    ollowing
    -1.39
    POSITIVE LOGITS
    art
    1.67
    map
    1.66
    imb
    1.55
    ong
    1.50
    uy
    1.48
    \'
    1.45
    oss
    1.39
    into
    1.39
     win
    1.37
    onen
    1.35
    Activations Density 0.109%

    No Known Activations