© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27702
    Prev
    Next
    INDEX
    Explanations

    references to fundraising

    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
    1.0%
    463
    +0.13
    0.8%
    191
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.16
    0.02
    174
    +0.13
    0.02
    191
    +0.12
    0.02
    Negative Logits
     widely
    -1.60
    áĢº
    -1.56
    UGH
    -1.55
     heavily
    -1.53
     happier
    -1.51
    blogger
    -1.51
    woke
    -1.50
     stark
    -1.50
    ingle
    -1.49
     sharply
    -1.47
    POSITIVE LOGITS
    ģ
    2.44
    ī
    2.43
    Ħ
    2.41
    ľ
    2.29
    °
    2.25
    ŀ
    2.25
    notes
    2.23
    Ģ
    2.11
    ľĵ
    2.09
    raiser
    2.07
    Activations Density 3.190%

    No Known Activations