© 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. 25585
    Prev
    Next
    INDEX
    Explanations

    instances of the token "ip."

    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
    376
    +0.11
    0.6%
    308
    +0.10
    0.6%
    164
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.11
    0.03
    293
    +0.10
    0.03
    24
    +0.10
    0.03
    Negative Logits
    ĸ´
    -2.86
    ¿½
    -2.66
    Ĥ¬
    -2.62
    Ĥ
    -2.46
    »
    -2.42
    Īĺ
    -2.41
    ¼
    -2.40
    Ļª
    -2.38
    ¿
    -2.35
    Į
    -2.35
    POSITIVE LOGITS
    edia
    1.83
    nik
    1.67
    ulation
    1.59
    nement
    1.52
    cie
    1.48
     yields
    1.46
    tech
    1.45
    endor
    1.44
    ository
    1.43
    lane
    1.40
    Activations Density 0.243%

    No Known Activations