© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26340
    Prev
    Next
    INDEX
    Explanations

    situations described as challenging or difficult

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.21
    1.2%
    457
    +0.15
    0.9%
    148
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.21
    0.02
    457
    +0.15
    0.02
    14
    +0.14
    0.02
    Negative Logits
    omorphisms
    -1.57
    uge
    -1.51
    said
    -1.49
    ofl
    -1.47
    >'
    -1.43
    urer
    -1.40
    uw
    -1.38
    oddsidemargin
    -1.37
     dass
    -1.34
    erl
    -1.33
    POSITIVE LOGITS
    ľĵ
    2.83
    ¬
    2.61
    ł
    2.54
    Ĥ¬
    2.53
    Ł
    2.45
    ¢
    2.40
    Ļª
    2.29
    ĩ
    2.27
    ¤
    2.25
    ´
    2.22
    Activations Density 0.018%

    No Known Activations