© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 8696
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or values

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    78
    +0.19
    1.1%
    21
    +0.16
    0.9%
    287
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.19
    0.01
    28
    +0.16
    0.03
    21
    +0.11
    0.03
    Negative Logits
    ality
    -1.72
     regard
    -1.65
    encies
    -1.61
     possession
    -1.52
     respect
    -1.49
    aries
    -1.49
    soever
    -1.40
    ary
    -1.39
    pered
    -1.38
    hold
    -1.37
    POSITIVE LOGITS
    xffffffff
    3.32
    xff
    3.24
    xFF
    3.23
    xffff
    3.19
    xb
    2.87
    xC
    2.78
    xA
    2.76
    xE
    2.62
    xF
    2.62
    xa
    2.60
    Activations Density 0.229%

    No Known Activations