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. 27529
    Prev
    Next
    INDEX
    Explanations

    mentions of arrangements or agreements

    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
    156
    +0.18
    1.0%
    376
    +0.15
    0.9%
    144
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.18
    0.01
    144
    +0.15
    0.01
    426
    +0.12
    0.01
    Negative Logits
     anybody
    -1.90
     anyone
    -1.67
     beating
    -1.60
     tomorrow
    -1.55
     riders
    -1.49
    cies
    -1.44
     somebody
    -1.42
     Acad
    -1.41
     Publ
    -1.39
    cca
    -1.38
    POSITIVE LOGITS
    veolar
    2.15
    isms
    1.98
    igue
    1.88
    ilateral
    1.79
    elines
    1.78
    ismatic
    1.76
    imen
    1.75
    tery
    1.72
    ism
    1.64
    etable
    1.62
    Activations Density 0.008%

    No Known Activations