Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27350
    Prev
    Next
    INDEX
    Explanations

    mentions of wages and minimum wage issues

    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
    219
    +0.16
    0.9%
    376
    +0.14
    0.8%
    250
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.16
    0.02
    167
    +0.14
    0.02
    85
    +0.12
    0.02
    Negative Logits
    uke
    -1.53
     FIG
    -1.45
     mention
    -1.40
    \)
    -1.35
     Cause
    -1.34
     interest
    -1.32
     Sea
    -1.29
     Empire
    -1.29
    usions
    -1.27
    allel
    -1.26
    POSITIVE LOGITS
    wright
    1.79
    ENTIAL
    1.72
    "}](#
    1.67
    ably
    1.55
    etable
    1.48
    kowski
    1.48
    haus
    1.47
    epi
    1.45
     suffers
    1.45
    schemas
    1.44
    Activations Density 0.019%

    No Known Activations