© 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. 29134
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of formation or establishing something

    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
    +0.12
    0.7%
    376
    +0.12
    0.7%
    217
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.12
    0.02
    430
    +0.12
    0.01
    467
    +0.12
    0.01
    Negative Logits
     ÑĩÑĤо
    -1.86
    adoc
    -1.61
     sale
    -1.59
    ĻĤ
    -1.52
    unnumbered
    -1.47
     somebody
    -1.47
     sell
    -1.46
     pound
    -1.45
    woke
    -1.45
    ½
    -1.43
    POSITIVE LOGITS
    arily
    2.04
    idable
    1.76
     occurs
    1.71
     modes
    1.70
    hesis
    1.62
     occurring
    1.56
    chart
    1.53
    ontal
    1.52
     process
    1.49
    grounds
    1.48
    Activations Density 0.047%

    No Known Activations