© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25575
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and documentation related to property or civil rights

    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%
    341
    +0.11
    0.6%
    216
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.11
    0.06
    155
    +0.11
    0.11
    341
    +0.11
    0.09
    Negative Logits
    lite
    -1.64
    onds
    -1.63
    ulos
    -1.53
    tab
    -1.48
     tons
    -1.48
    ements
    -1.47
     sites
    -1.46
     jobs
    -1.44
    ium
    -1.39
    chat
    -1.39
    POSITIVE LOGITS
    2.52
    2.52
    2.52
    2.52
    ↵↵
    2.52
    <|outofrange|>
    2.52
                ↵
    2.52
    ↵
    2.52
    ↵
    2.52
    <|outofrange|>
    2.52
    Activations Density 2.296%

    No Known Activations