© 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. 30321
    Prev
    Next
    INDEX
    Explanations

    attributes or parameters defined in a code or data structure

    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
    478
    +0.17
    1.0%
    165
    +0.13
    0.7%
    380
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    261
    +0.17
    0.08
    227
    +0.13
    0.09
    155
    +0.12
    0.07
    Negative Logits
     position
    -1.63
    ģ
    -1.62
    ](
    -1.49
     ago
    -1.47
    ī
    -1.47
     erred
    -1.47
     standpoint
    -1.45
     era
    -1.45
     accurately
    -1.44
     retrieved
    -1.44
    POSITIVE LOGITS
    icul
    1.66
    tsd
    1.64
    my
    1.49
    rolling
    1.47
    thro
    1.47
     clot
    1.45
    nar
    1.40
    panic
    1.40
    their
    1.38
    nae
    1.37
    Activations Density 0.294%

    No Known Activations