© 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. 0-MLP-SM
    11. 28661
    Prev
    Next
    INDEX
    Explanations

    instances of the word "traverse" in various forms

    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
    148
    +0.16
    0.9%
    232
    +0.12
    0.6%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.01
    148
    +0.12
    0.01
    200
    +0.11
    0.01
    Negative Logits
     proper
    -1.47
    ctomy
    -1.45
     hosting
    -1.44
     hosts
    -1.43
    rame
    -1.41
    ctor
    -1.38
    uge
    -1.32
     otherwise
    -1.30
     investigators
    -1.29
     appropriate
    -1.28
    POSITIVE LOGITS
    Ĵ
    3.13
    ©
    3.00
    Ĩ
    2.78
    ¶
    2.77
    ¹
    2.64
    ¤
    2.62
    ¾
    2.61
    IJ
    2.61
    ¨
    2.61
    º
    2.60
    Activations Density 0.013%

    No Known Activations