© 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. 31836
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals

    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
    +0.28
    1.6%
    369
    +0.20
    1.2%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.28
    0.12
    369
    +0.20
    0.06
    43
    +0.13
    0.04
    Negative Logits
    ordinate
    -1.67
    unct
    -1.56
    "}](#
    -1.53
    esides
    -1.52
    coding
    -1.47
    hering
    -1.45
     particular
    -1.44
    ortion
    -1.44
    aying
    -1.42
    unes
    -1.40
    POSITIVE LOGITS
     Award
    1.97
     Bros
    1.93
     Street
    1.84
     Prize
    1.82
    pton
    1.80
    ville
    1.80
     Brothers
    1.78
     County
    1.78
    esque
    1.75
    ian
    1.74
    Activations Density 0.743%

    No Known Activations