© 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. 22835
    Prev
    Next
    INDEX
    Explanations

    statements concerning inspections and evaluations related to Iraq's compliance

    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
    455
    +0.11
    0.6%
    401
    +0.10
    0.6%
    35
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.11
    0.11
    356
    +0.10
    0.10
    246
    +0.10
    0.11
    Negative Logits
     families
    -1.66
     minority
    -1.58
    quired
    -1.57
     guys
    -1.49
    kees
    -1.39
     masters
    -1.37
     teams
    -1.35
     extensive
    -1.34
     minorities
    -1.33
     engineers
    -1.32
    POSITIVE LOGITS
    ↵
    2.75
    2.75
    ↵
    2.75
    2.75
    ↵↵↵
    2.75
              ↵
    2.75
    č↵
    2.75
    ↵↵
    2.75
     ↵
    2.75
    <|outofrange|>
    2.75
    Activations Density 2.146%

    No Known Activations