© 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. 29644
    Prev
    Next
    INDEX
    Explanations

    references to biological processes and concepts

    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
    +0.19
    1.1%
    61
    +0.13
    0.8%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.19
    0.02
    320
    +0.13
    0.01
    110
    +0.11
    0.01
    Negative Logits
    asty
    -1.58
    uber
    -1.57
    astern
    -1.55
    fasterxml
    -1.48
    oxacin
    -1.39
     Healthy
    -1.37
    wegian
    -1.35
    ahoma
    -1.35
    hentication
    -1.34
    roelectric
    -1.33
    POSITIVE LOGITS
    ĺ
    2.29
    ¡
    2.21
    ĻĤ
    2.20
    ij
    2.03
    ļ
    2.03
    ł
    1.96
    ¾
    1.93
    Ļ
    1.89
    Īĺ
    1.89
    iom
    1.84
    Activations Density 0.535%

    No Known Activations