© 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 EvalsExportsAPI 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. 29158
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "with"

    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
    +0.30
    1.8%
    69
    +0.20
    1.2%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.30
    0.16
    245
    +0.20
    0.12
    358
    +0.14
    0.11
    Negative Logits
    ÅĽci
    -1.80
    liche
    -1.70
    ock
    -1.68
    iph
    -1.68
    igraph
    -1.66
    og
    -1.61
    mente
    -1.55
    ben
    -1.54
    Âł
    -1.53
    hell
    -1.52
    POSITIVE LOGITS
     respect
    3.12
     regard
    2.93
     regards
    2.76
     slightest
    2.10
     any
    2.02
     respects
    1.85
     deference
    1.85
     seriousness
    1.76
     disparate
    1.75
     your
    1.75
    Activations Density 4.108%

    No Known Activations