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. 27295
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups of people

    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
    +0.21
    1.2%
    376
    +0.18
    1.0%
    365
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.21
    0.01
    241
    +0.18
    0.02
    65
    +0.16
    0.02
    Negative Logits
    Ĵ
    -2.20
    ·
    -2.05
    ĥ
    -2.04
    §
    -1.94
    ·¸
    -1.88
    ĵ
    -1.88
    į
    -1.85
    ³
    -1.80
    ¸
    -1.78
    Ħ
    -1.78
    POSITIVE LOGITS
    uscript
    1.88
    iscus
    1.86
     ago
    1.85
    agem
    1.82
    hole
    1.75
     identifier
    1.74
    illar
    1.60
    ilent
    1.59
    dag
    1.59
    ystems
    1.58
    Activations Density 0.018%

    No Known Activations