© 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. 1-RES-SM
    11. 25717
    Prev
    Next
    INDEX
    Explanations

    references to projects and research studies involving personal participation

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    98
    +0.16
    0.9%
    476
    +0.13
    0.7%
    329
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.16
    0.03
    157
    +0.13
    0.03
    476
    +0.11
    0.03
    Negative Logits
     pleasure
    -1.72
    ities
    -1.72
     sensations
    -1.64
    tons
    -1.50
     sensation
    -1.49
     attent
    -1.48
    Decided
    -1.44
     phantom
    -1.42
     behaviour
    -1.41
    rous
    -1.41
    POSITIVE LOGITS
    Īĺ
    2.33
    ¡
    2.21
    »¿
    2.20
    £
    1.98
    ģ
    1.92
    °
    1.92
    ½
    1.91
    ij
    1.90
    IJ
    1.88
    ¹
    1.88
    Activations Density 0.184%

    No Known Activations