© 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. 30642
    Prev
    Next
    INDEX
    Explanations

    instances of the word "consideration."

    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
    376
    +0.17
    1.0%
    10
    +0.13
    0.8%
    100
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.17
    0.01
    10
    +0.13
    0.01
    416
    +0.13
    0.01
    Negative Logits
    ĥ½
    -1.92
    MOESM
    -1.89
    Ĵ
    -1.82
    ¿½
    -1.70
    ĨĴ
    -1.66
    Į
    -1.64
    liest
    -1.58
    >&
    -1.52
    »
    -1.50
    imony
    -1.48
    POSITIVE LOGITS
    ately
    1.54
    ière
    1.54
     needs
    1.50
     processor
    1.50
     acquisition
    1.50
     pressures
    1.47
    lessly
    1.44
     sized
    1.42
     defaults
    1.41
     area
    1.38
    Activations Density 0.668%

    No Known Activations