© 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. 28177
    Prev
    Next
    INDEX
    Explanations

    terms related to perceptions and subjective experiences

    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
    +0.17
    0.9%
    391
    +0.15
    0.8%
    148
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.17
    0.01
    391
    +0.15
    0.01
    429
    +0.13
    0.01
    Negative Logits
    enu
    -1.75
    els
    -1.65
    taire
    -1.64
    amais
    -1.63
    blockList
    -1.61
    amed
    -1.52
    apter
    -1.51
    smith
    -1.50
     Honorable
    -1.50
    coli
    -1.44
    POSITIVE LOGITS
     worse
    1.68
     least
    1.50
    1.46
     better
    1.45
     unity
    1.37
     viewing
    1.36
     own
    1.36
     otherwise
    1.35
     spot
    1.34
    itious
    1.34
    Activations Density 0.166%

    No Known Activations