© 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. 29848
    Prev
    Next
    INDEX
    Explanations

    references to a "medium" quality or size in various contexts

    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
    385
    +0.15
    0.9%
    457
    +0.12
    0.7%
    500
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.15
    0.04
    53
    +0.12
    0.04
    56
    +0.12
    0.01
    Negative Logits
    opropyl
    -1.77
     plaintiffs
    -1.66
     Mice
    -1.65
     highly
    -1.62
     appellants
    -1.60
     prey
    -1.54
     bitterly
    -1.54
     mice
    -1.53
     victims
    -1.52
     tear
    -1.49
    POSITIVE LOGITS
    forge
    1.90
    tables
    1.80
    oon
    1.79
    ician
    1.77
    eries
    1.77
    tube
    1.76
    finals
    1.73
    wave
    1.69
    boro
    1.68
    speed
    1.68
    Activations Density 4.968%

    No Known Activations