© 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. 2-MLP-SM
    6. 25942
    Prev
    Next
    INDEX
    Explanations

    references to guiding principles or helpful advice

    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
    419
    +0.12
    0.7%
    459
    +0.12
    0.7%
    133
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.12
    0.11
    459
    +0.12
    0.13
    465
    +0.11
    0.14
    Negative Logits
    ¦
    -1.94
    Ļª
    -1.91
    °
    -1.87
    ¿½
    -1.83
    §
    -1.82
    Ĺ
    -1.80
    ľ
    -1.79
    ¿
    -1.74
    ł
    -1.71
    ĨĴ
    -1.69
    POSITIVE LOGITS
    ury
    1.74
    haul
    1.62
     bodies
    1.56
    ake
    1.53
     owing
    1.48
    bsite
    1.47
    ache
    1.39
     circulation
    1.35
    ophone
    1.34
    .$
    1.34
    Activations Density 2.256%

    No Known Activations