© 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. 26319
    Prev
    Next
    INDEX
    Explanations

    references to integration in various contexts

    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
    +0.18
    1.0%
    178
    +0.12
    0.7%
    338
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.18
    0.01
    340
    +0.12
    0.01
    469
    +0.10
    0.01
    Negative Logits
     anybody
    -1.93
     anyone
    -1.88
    ĨĴ
    -1.85
    orems
    -1.84
    ĻĤ
    -1.78
    rceil
    -1.76
    Ļª
    -1.73
    Ļ
    -1.68
     anything
    -1.67
    ubicin
    -1.64
    POSITIVE LOGITS
     controls
    1.96
    osa
    1.77
     centers
    1.77
     era
    1.70
     site
    1.65
     zones
    1.62
     factor
    1.61
     centres
    1.55
     mode
    1.54
     effect
    1.52
    Activations Density 0.711%

    No Known Activations