© 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. 26579
    Prev
    Next
    INDEX
    Explanations

    instances of the word "iss" or related variations

    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
    191
    +0.14
    0.8%
    376
    +0.12
    0.7%
    334
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.14
    0.02
    13
    +0.12
    0.02
    334
    +0.10
    0.01
    Negative Logits
    upon
    -1.60
    LLOW
    -1.47
     sense
    -1.43
     meaning
    -1.41
    laid
    -1.36
    ought
    -1.35
    ?_
    -1.34
     entire
    -1.33
    cause
    -1.33
    STER
    -1.32
    POSITIVE LOGITS
    etto
    1.80
    ftware
    1.61
    etts
    1.59
    ness
    1.58
    ière
    1.56
    burg
    1.54
    enstein
    1.54
    court
    1.52
    etta
    1.51
    iorari
    1.48
    Activations Density 0.017%

    No Known Activations