© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-MLP-SM
    11. 28062
    Prev
    Next
    INDEX
    Explanations

    terms related to security vulnerabilities

    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
    71
    +0.10
    0.6%
    445
    +0.10
    0.6%
    206
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.10
    0.01
    387
    +0.10
    0.01
    398
    +0.10
    0.01
    Negative Logits
    Ĥ
    -1.73
    ¿
    -1.64
    unnumbered
    -1.62
    ¸
    -1.60
    µ
    -1.59
    ³
    -1.57
    cker
    -1.56
     gay
    -1.52
    »¿
    -1.50
     href
    -1.48
    POSITIVE LOGITS
    ilated
    1.79
     situation
    1.70
    tee
    1.70
     passages
    1.63
     situations
    1.62
     fits
    1.58
     ('
    1.57
    osa
    1.57
    wise
    1.53
     itself
    1.51
    Activations Density 0.024%

    No Known Activations