© 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. 31472
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to various aspects of design, fashion, and real estate

    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
    156
    +0.36
    2.2%
    218
    +0.12
    0.7%
    140
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.36
    0.19
    71
    +0.12
    0.19
    437
    +0.11
    0.17
    Negative Logits
    Īĺ
    -4.11
    ĸ´
    -3.86
    ĥ½
    -3.69
    »
    -3.68
    į
    -3.68
    ↵
    -3.68
    <|outofrange|>
    -3.68
    č↵
    -3.68
     ↵
    -3.68
    -3.68
    POSITIVE LOGITS
     industry
    2.17
     enthusi
    2.05
     department
    2.04
     enthusiasts
    1.78
     distributor
    1.72
    listed
    1.72
     fans
    1.72
     franchise
    1.69
     awards
    1.69
     club
    1.68
    Activations Density 2.672%

    No Known Activations