© 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. 25323
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks often found in formal documents or code

    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
    83
    +0.13
    0.7%
    347
    +0.12
    0.7%
    224
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.13
    0.03
    500
    +0.12
    0.03
    123
    +0.11
    0.03
    Negative Logits
    ĻĤ
    -1.56
     girls
    -1.49
     bill
    -1.47
     Montana
    -1.35
    BACK
    -1.35
     stret
    -1.34
     http
    -1.27
    sudo
    -1.26
     cents
    -1.26
     corps
    -1.25
    POSITIVE LOGITS
    imum
    1.78
     itself
    1.61
    Å¡ÃŃ
    1.57
    icial
    1.50
    hest
    1.48
    etter
    1.47
     induct
    1.43
     recurs
    1.41
    omitempty
    1.40
    vic
    1.40
    Activations Density 1.702%

    No Known Activations