© 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. 30859
    Prev
    Next
    INDEX
    Explanations

    instances of quotes or dialogue in the text

    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
    9
    +0.13
    0.7%
    11
    +0.12
    0.7%
    97
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.13
    0.08
    340
    +0.12
    0.07
    261
    +0.12
    0.06
    Negative Logits
    disambiguation
    -1.62
    arest
    -1.60
    ductive
    -1.60
    optera
    -1.57
     cells
    -1.33
     town
    -1.32
    acea
    -1.32
    ľ
    -1.31
     cell
    -1.31
    igator
    -1.30
    POSITIVE LOGITS
     effort
    1.55
    filled
    1.48
    LY
    1.47
    lights
    1.46
    !!!!
    1.44
    ively
    1.42
    fully
    1.38
    !”
    1.38
    ously
    1.34
    MENT
    1.32
    Activations Density 0.060%

    No Known Activations