© 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. 2-RES-SM
    11. 9738
    Prev
    Next
    INDEX
    Explanations

    references to various types of metals and their applications

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.22
    1.3%
    275
    +0.13
    0.7%
    446
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.22
    0.01
    1
    +0.13
    0.02
    424
    +0.12
    0.01
    Negative Logits
     hers
    -2.03
     wait
    -1.66
     yours
    -1.65
     place
    -1.64
     duration
    -1.45
    ção
    -1.45
     pituitary
    -1.44
     speech
    -1.41
     '../
    -1.41
     awake
    -1.41
    POSITIVE LOGITS
    lite
    1.75
    finger
    1.69
    anguage
    1.62
    hammer
    1.61
     herself
    1.61
    core
    1.61
    enium
    1.59
    isty
    1.58
    erated
    1.57
     detectors
    1.57
    Activations Density 0.064%

    No Known Activations