© 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. 2-RES-SM
    11. 27690
    Prev
    Next
    INDEX
    Explanations

    references to safety and security in various contexts

    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/2-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.2.hook_resid_post
    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
    360
    +0.15
    0.9%
    306
    +0.14
    0.8%
    386
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.15
    0.03
    306
    +0.14
    0.03
    426
    +0.12
    0.02
    Negative Logits
    £
    -2.71
    Īĺ
    -2.25
    ı
    -2.23
    ©
    -2.23
    ª
    -2.13
    ħ
    -2.07
    Ĭ
    -2.06
    ĵ
    -2.04
    Į
    -2.02
    »¿
    -2.02
    POSITIVE LOGITS
     reasons
    1.82
     mechanisms
    1.78
     regulations
    1.75
     clearance
    1.74
     zones
    1.74
     mechanism
    1.74
     considerations
    1.69
    "}](#
    1.68
     components
    1.68
     margin
    1.68
    Activations Density 0.110%

    No Known Activations