© 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. 24080
    Prev
    Next
    INDEX
    Explanations

    terms related to accreditation and certification processes

    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
    23
    +0.16
    0.9%
    190
    +0.14
    0.8%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.04
    478
    +0.14
    0.11
    410
    +0.11
    0.03
    Negative Logits
    ifies
    -1.83
    itud
    -1.73
    ificate
    -1.72
    aches
    -1.72
    ierno
    -1.67
    idas
    -1.65
    iverse
    -1.64
    ifications
    -1.61
    ")]
    -1.55
    etto
    -1.53
    POSITIVE LOGITS
     welcome
    1.64
    ĵ
    1.63
     much
    1.58
     nerves
    1.56
    Ī
    1.53
    USS
    1.52
     heterozygous
    1.52
     teens
    1.50
     nerve
    1.46
     surprise
    1.44
    Activations Density 1.869%

    No Known Activations