© 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. 24825
    Prev
    Next
    INDEX
    Explanations

    references to viewing or consuming visual 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/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
    219
    +0.12
    0.7%
    341
    +0.11
    0.6%
    181
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.12
    0.04
    33
    +0.11
    0.03
    182
    +0.11
    0.04
    Negative Logits
    teen
    -1.67
    panic
    -1.55
    obbsee
    -1.54
    ellow
    -1.48
    aly
    -1.45
     flush
    -1.45
    elly
    -1.44
    ellaneous
    -1.43
    FIL
    -1.43
     glow
    -1.39
    POSITIVE LOGITS
    £
    2.71
    Ł
    2.67
    ŀ
    2.61
    Ľ
    2.42
    «
    2.41
    ļ
    2.40
    Ĺ
    2.39
    ²
    2.34
    ł
    2.32
    ij
    2.28
    Activations Density 0.339%

    No Known Activations