© 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. 23975
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activity and firearms

    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
    448
    +0.17
    1.0%
    312
    +0.13
    0.7%
    333
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.17
    0.06
    190
    +0.13
    0.08
    123
    +0.13
    0.04
    Negative Logits
    ered
    -1.84
     sexually
    -1.82
    ished
    -1.79
     terminated
    -1.64
     reportedly
    -1.59
     disappeared
    -1.57
     yelled
    -1.57
    Ļª
    -1.54
    ĻĤ
    -1.53
     confirmed
    -1.52
    POSITIVE LOGITS
    schemas
    1.79
    past
    1.73
    Simplify
    1.61
    ERC
    1.58
    prep
    1.53
    orb
    1.51
    canonical
    1.50
    oracle
    1.49
    krit
    1.48
    '}$
    1.48
    Activations Density 1.964%

    No Known Activations