© 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. 27719
    Prev
    Next
    INDEX
    Explanations

    mentions of advertisements and advert content

    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
    +0.27
    1.7%
    221
    +0.14
    0.9%
    376
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.27
    0.02
    109
    +0.14
    0.01
    250
    +0.12
    0.01
    Negative Logits
    TRODUCTION
    -1.62
     else
    -1.45
    documentclass
    -1.44
     sudden
    -1.41
    quartile
    -1.40
    isex
    -1.39
    Argued
    -1.38
    jours
    -1.35
    rapeutics
    -1.34
     Ski
    -1.30
    POSITIVE LOGITS
    icum
    1.80
    pora
    1.68
    iction
    1.64
    ios
    1.60
    ue
    1.60
    ong
    1.60
    opan
    1.58
    lei
    1.58
    ilate
    1.57
    uits
    1.56
    Activations Density 0.022%

    No Known Activations