© 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. 29673
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and legal issues

    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
    156
    +0.20
    1.2%
    356
    +0.11
    0.6%
    233
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.20
    0.01
    156
    +0.11
    0.03
    111
    +0.10
    0.03
    Negative Logits
    'd
    -1.70
     clicked
    -1.65
    :/
    -1.62
    rians
    -1.50
    rid
    -1.49
    ':
    -1.47
     vacant
    -1.47
     thumbs
    -1.46
     Dylan
    -1.45
     blown
    -1.44
    POSITIVE LOGITS
    iral
    1.74
     remains
    1.67
    osi
    1.62
    osa
    1.53
     scenario
    1.52
    ski
    1.51
    ose
    1.48
    ises
    1.48
    forms
    1.47
     theory
    1.47
    Activations Density 0.110%

    No Known Activations