© 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. 0-MLP-SM
    11. 29273
    Prev
    Next
    INDEX
    Explanations

    technical terms related to security and encryption

    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
    410
    +0.19
    1.1%
    162
    +0.15
    0.9%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.19
    0.09
    276
    +0.15
    0.08
    225
    +0.11
    0.08
    Negative Logits
     me
    -1.47
     faithful
    -1.43
     regeneration
    -1.42
     strength
    -1.40
    ontrol
    -1.39
     dear
    -1.38
    hip
    -1.35
    ances
    -1.34
     maiden
    -1.34
     regener
    -1.32
    POSITIVE LOGITS
    shots
    1.81
    iston
    1.69
    like
    1.64
    ÃŃc
    1.45
    curve
    1.44
    SQL
    1.41
     aboard
    1.41
    "}](#
    1.40
    etto
    1.39
    erton
    1.38
    Activations Density 1.561%

    No Known Activations