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

    Neuronpedia

    Jacobian LensNEW
    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. 24588
    Prev
    Next
    INDEX
    Explanations

    references to financial implications or monetary values

    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
    395
    +0.15
    0.9%
    387
    +0.12
    0.7%
    72
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.15
    0.10
    108
    +0.12
    0.07
    387
    +0.11
    0.07
    Negative Logits
    ights
    -1.66
    xi
    -1.66
     beginning
    -1.60
    ching
    -1.57
    acing
    -1.56
    ox
    -1.56
    iating
    -1.54
    chy
    -1.52
     magnitudes
    -1.50
    iated
    -1.49
    POSITIVE LOGITS
    ↵  âĢĥ
    2.96
    2.96
    č↵
    2.96
    ↵
    2.96
    <|outofrange|>
    2.96
    ↵
    2.96
    <|outofrange|>
    2.96
    ↵↵
    2.96
    <|outofrange|>
    2.96
    ↵↵↵
    2.96
    Activations Density 0.736%

    No Known Activations