© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12123
    Prev
    Next
    INDEX
    Explanations

    negative statements or expressions

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.28
    1.7%
    156
    +0.24
    1.5%
    78
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.28
    0.05
    255
    +0.24
    0.00
    448
    +0.16
    0.06
    Negative Logits
    umab
    -1.58
    oplasty
    -1.56
    imet
    -1.45
    rophy
    -1.38
    nier
    -1.37
     rehabilitation
    -1.31
    rendum
    -1.30
    otherapy
    -1.26
     tub
    -1.25
    olateral
    -1.25
    POSITIVE LOGITS
     debugging
    1.56
    compat
    1.53
     =>
    1.52
    readable
    1.52
    esque
    1.46
     ubuntu
    1.46
    tagged
    1.45
     Ubuntu
    1.43
    browser
    1.42
    utils
    1.41
    Activations Density 0.248%

    No Known Activations