© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26438
    Prev
    Next
    INDEX
    Explanations

    items of clothing, particularly various types of skirts, dresses, and pants

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.11
    0.6%
    220
    +0.10
    0.6%
    162
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.11
    0.03
    410
    +0.10
    0.02
    277
    +0.10
    0.07
    Negative Logits
    ·
    -4.16
    ¼
    -4.15
    Ļ
    -4.12
    İ
    -3.99
    °
    -3.96
    §
    -3.88
    ©
    -3.88
    Ń
    -3.85
    Ĵ
    -3.85
    ĺ
    -3.83
    POSITIVE LOGITS
    "));
    1.65
    ";
    1.50
    ").
    1.48
    eer
    1.48
    ubicin
    1.47
    "—
    1.45
    phrine
    1.41
    ylum
    1.35
     Borough
    1.33
     Lieutenant
    1.30
    Activations Density 1.577%

    No Known Activations