© 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 EvalsExportsAPI 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. 28433
    Prev
    Next
    INDEX
    Explanations

    terms related to immunology

    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
    111
    +0.14
    0.8%
    125
    +0.12
    0.7%
    71
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.05
    243
    +0.12
    0.04
    98
    +0.12
    0.02
    Negative Logits
     same
    -1.76
    =".
    -1.50
     truly
    -1.48
    unting
    -1.40
     respectively
    -1.38
    ĨĴ
    -1.35
    comes
    -1.30
    ="@+
    -1.30
     successful
    -1.26
     Matthews
    -1.24
    POSITIVE LOGITS
    pect
    1.79
    ity
    1.76
    ités
    1.63
    uar
    1.60
    icult
    1.58
    aceae
    1.54
    ized
    1.51
    oprecip
    1.51
    orest
    1.48
    olved
    1.48
    Activations Density 1.233%

    No Known Activations