© 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. 26808
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "Jekyll"

    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
    474
    +0.13
    0.7%
    399
    +0.12
    0.7%
    307
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.13
    0.01
    399
    +0.12
    0.01
    279
    +0.11
    0.01
    Negative Logits
    »¿
    -2.20
    Īĺ
    -1.84
    Ļ
    -1.83
    ¿½
    -1.78
    ¾
    -1.76
    ¿
    -1.73
    ½
    -1.71
    Ĺ
    -1.64
    »
    -1.52
    yline
    -1.50
    POSITIVE LOGITS
    ieu
    1.45
    mong
    1.44
    fest
    1.41
    bench
    1.40
    ière
    1.39
    witz
    1.39
    iop
    1.38
    ingly
    1.36
    iterate
    1.36
    bank
    1.35
    Activations Density 0.015%

    No Known Activations