© 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. 28893
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the word "tit" and variations of the word "title"

    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
    410
    +0.17
    1.0%
    324
    +0.13
    0.8%
    249
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.17
    0.01
    410
    +0.13
    0.01
    249
    +0.12
    0.01
    Negative Logits
    Ļª
    -2.30
    Ĺ
    -1.89
    ĵ
    -1.85
    ĸ´
    -1.83
    ↵
    -1.80
    č↵
    -1.80
    -1.80
    -1.80
    -1.80
    -1.80
    POSITIVE LOGITS
    blr
    1.87
    shots
    1.65
    ious
    1.59
    locked
    1.51
    idity
    1.51
    ivated
    1.51
    etable
    1.49
    gif
    1.48
    aurus
    1.47
    aho
    1.47
    Activations Density 0.007%

    No Known Activations