© 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 EvalsExportsAPI 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. 24445
    Prev
    Next
    INDEX
    Explanations

    HTML and XML markup elements and attributes

    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
    186
    +0.11
    0.6%
    235
    +0.11
    0.6%
    223
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.11
    0.05
    235
    +0.11
    0.05
    421
    +0.11
    0.05
    Negative Logits
    rangle
    -1.68
    ash
    -1.53
    ermanent
    -1.45
    Ĺ
    -1.44
    otted
    -1.43
    reek
    -1.40
    ocate
    -1.37
    rvert
    -1.37
    oxylin
    -1.36
    illed
    -1.36
    POSITIVE LOGITS
     vez
    1.71
    pson
    1.63
    sense
    1.60
     prejudice
    1.55
     SI
    1.52
    etts
    1.47
    cies
    1.46
     striker
    1.43
     unanim
    1.43
    mann
    1.42
    Activations Density 0.270%

    No Known Activations