© 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. Residuals
    9. 4-RES-SM
    11. 10067
    Prev
    Next
    INDEX
    Explanations

    specific terms related to cybersecurity discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.36
    4.1%
    78
    +0.24
    2.7%
    9
    +0.10
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.36
    0.45
    271
    +0.24
    0.09
    156
    +0.10
    0.40
    Negative Logits
    ĥ½
    -1.71
    ĸ´
    -1.70
    ↵↵
    -1.57
    -1.57
    -1.57
    -1.57
      ↵
    -1.57
    ↵↵
    -1.57
    -1.57
    -1.57
    POSITIVE LOGITS
    )$)
    1.22
    imester
    1.21
    iston
    1.13
    forth
    1.06
    ))/((-
    1.05
    pinion
    1.03
    ))/(-
    1.02
     werden
    1.02
    )))**
    1.01
    inger
    1.01
    Activations Density 8.987%

    No Known Activations