© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    terms related to community engagement and communication

    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
    +0.19
    1.1%
    326
    +0.12
    0.7%
    9
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.19
    0.03
    21
    +0.12
    0.01
    9
    +0.12
    0.02
    Negative Logits
    upon
    -1.32
    lessly
    -1.29
    kins
    -1.28
    ful
    -1.28
    PE
    -1.26
    herry
    -1.25
     industry
    -1.24
    brains
    -1.22
    PhysRev
    -1.20
    anian
    -1.20
    POSITIVE LOGITS
    ications
    2.59
    icating
    2.56
    ication
    2.41
    icable
    2.23
    icates
    2.19
    icate
    2.11
    icated
    2.09
    icator
    1.98
    ±
    1.85
    es
    1.83
    Activations Density 0.185%

    No Known Activations