© 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. 9629
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and details about people's lives

    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
    358
    +0.17
    1.0%
    263
    +0.13
    0.7%
    27
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.17
    0.18
    455
    +0.13
    0.14
    88
    +0.12
    0.11
    Negative Logits
     respectively
    -1.79
     remainder
    -1.53
     confirmation
    -1.40
     Ground
    -1.39
    zitter
    -1.36
     Shield
    -1.36
    ĻĤ
    -1.35
     appearances
    -1.32
     motions
    -1.30
     attacks
    -1.29
    POSITIVE LOGITS
    "}](#
    1.62
    /?
    1.54
     copyrighted
    1.53
    herty
    1.49
     groove
    1.49
     craving
    1.48
    https
    1.41
     ;;
    1.40
    /-/
    1.38
    http
    1.37
    Activations Density 4.380%

    No Known Activations