© 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. 27564
    Prev
    Next
    INDEX
    Explanations

    the name "Robert" 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
    156
    +0.17
    1.0%
    410
    +0.14
    0.8%
    397
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.17
    0.05
    369
    +0.14
    0.02
    352
    +0.14
    0.02
    Negative Logits
    board
    -1.77
     current
    -1.67
    achusetts
    -1.66
    "}](#
    -1.59
    ibel
    -1.56
    rim
    -1.56
    ETHOD
    -1.55
    consin
    -1.55
    ibilit
    -1.53
    rapy
    -1.47
    POSITIVE LOGITS
    ±
    2.27
    ¹
    1.99
    ´
    1.89
    ¾
    1.73
    ¦
    1.71
    ·
    1.69
    º
    1.66
    ½
    1.63
    ľ
    1.62
    µ
    1.56
    Activations Density 0.174%

    No Known Activations