© 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. 2-MLP-SM
    11. 22733
    Prev
    Next
    INDEX
    Explanations

    occurrences of code or data formatting elements

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    59
    +0.12
    0.7%
    137
    +0.12
    0.6%
    215
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.12
    0.02
    400
    +0.12
    0.05
    474
    +0.12
    0.03
    Negative Logits
     Minutes
    -1.67
    inux
    -1.58
    heses
    -1.53
    :"
    -1.52
    thon
    -1.47
     tablet
    -1.44
    ://
    -1.44
     tablets
    -1.41
    _"
    -1.40
    :`
    -1.40
    POSITIVE LOGITS
    »¿
    1.69
    ĻĤ
    1.69
    ®
    1.65
     fare
    1.59
    ª
    1.59
    writers
    1.53
    idem
    1.51
    «
    1.50
    proving
    1.47
     Romney
    1.47
    Activations Density 0.379%

    No Known Activations