© 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. 25991
    Prev
    Next
    INDEX
    Explanations

    the use of slashes and URLs in a text

    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
    156
    +0.15
    0.8%
    348
    +0.11
    0.6%
    50
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.15
    0.02
    59
    +0.11
    0.01
    50
    +0.11
    0.02
    Negative Logits
    ît
    -1.66
    ticas
    -1.59
    unreadable
    -1.51
    ticos
    -1.48
    êm
    -1.46
    danger
    -1.44
    елÑĮ
    -1.43
    TEXT
    -1.42
    ãģı
    -1.39
    aining
    -1.39
    POSITIVE LOGITS
    Ī
    4.36
    İ
    3.83
    3.74
    č↵
    3.74
    ↵
    3.74
    ↵
    3.74
       ↵
    3.74
    3.74
    <|outofrange|>
    3.74
    <|outofrange|>
    3.74
    Activations Density 0.132%

    No Known Activations