© 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. 29467
    Prev
    Next
    INDEX
    Explanations

    references to anatomical structures in reptiles, particularly the hemipenes of male lizards

    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
    446
    +0.13
    0.7%
    347
    +0.12
    0.6%
    369
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.13
    0.01
    446
    +0.12
    0.01
    24
    +0.12
    0.01
    Negative Logits
     hereby
    -1.63
    hip
    -1.62
    hips
    -1.49
    ANCE
    -1.48
    ONS
    -1.44
    unreadable
    -1.44
    msgstr
    -1.43
    "`
    -1.43
     lieu
    -1.42
    deal
    -1.41
    POSITIVE LOGITS
    odynam
    1.93
    imeter
    1.81
    iei
    1.76
    odynamics
    1.73
    orro
    1.70
    isecond
    1.68
    blr
    1.63
    ibase
    1.61
    ifer
    1.58
    oo
    1.56
    Activations Density 0.124%

    No Known Activations