© 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. 29627
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spot."

    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
    +0.16
    0.9%
    148
    +0.14
    0.8%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.16
    0.02
    465
    +0.14
    0.02
    241
    +0.12
    0.02
    Negative Logits
     your
    -1.69
    ansen
    -1.58
     behalf
    -1.49
    аÑĪ
    -1.45
     drag
    -1.43
     Esq
    -1.43
     HREF
    -1.40
     Amazon
    -1.39
     pace
    -1.38
    ItemGroup
    -1.36
    POSITIVE LOGITS
    aneous
    1.99
    ting
    1.95
    borne
    1.80
    ty
    1.75
    less
    1.75
    lings
    1.69
    cules
    1.66
    lessness
    1.59
    ential
    1.59
    als
    1.58
    Activations Density 0.061%

    No Known Activations