© 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 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. 11119
    Prev
    Next
    INDEX
    Explanations

    phrases related to referencing sources or documentation

    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
    307
    +0.29
    1.7%
    306
    +0.15
    0.8%
    281
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.29
    0.09
    306
    +0.15
    0.05
    91
    +0.11
    0.05
    Negative Logits
    isters
    -1.64
    tics
    -1.62
    wide
    -1.61
     nevertheless
    -1.57
     nonetheless
    -1.52
    gang
    -1.43
    men
    -1.42
    istically
    -1.41
     thereof
    -1.41
    ument
    -1.40
    POSITIVE LOGITS
     docs
    2.64
     http
    2.48
     https
    2.31
     my
    2.25
     documentation
    2.11
     Wikipedia
    2.03
    ="#
    1.95
     comments
    1.89
     tutorials
    1.88
     xml
    1.88
    Activations Density 0.601%

    No Known Activations