© 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. 26318
    Prev
    Next
    INDEX
    Explanations

    references to connections or associations between different entities

    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
    +0.15
    0.8%
    91
    +0.11
    0.6%
    255
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.15
    0.01
    91
    +0.11
    0.01
    212
    +0.10
    0.01
    Negative Logits
     tolerated
    -1.49
     invasive
    -1.43
     celebrated
    -1.41
    ands
    -1.38
    llo
    -1.38
     boo
    -1.38
    tsd
    -1.35
    woke
    -1.35
    wered
    -1.32
    spe
    -1.30
    POSITIVE LOGITS
    ossier
    1.69
    enz
    1.61
    feit
    1.56
    ência
    1.47
    ĻĤ
    1.47
    ulif
    1.44
    iero
    1.43
     \$
    1.41
    \$
    1.38
    groupId
    1.36
    Activations Density 1.721%

    No Known Activations