© 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. 2-RES-SM
    11. 31726
    Prev
    Next
    INDEX
    Explanations

    elements related to licensing information in text

    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
    11
    +0.15
    0.8%
    302
    +0.14
    0.8%
    233
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.15
    0.01
    74
    +0.14
    0.01
    222
    +0.14
    0.01
    Negative Logits
    thro
    -1.53
     respectively
    -1.53
    autre
    -1.42
    '):
    -1.37
    during
    -1.36
    then
    -1.34
    AFFIRMED
    -1.33
     saline
    -1.32
    urban
    -1.32
    ipation
    -1.30
    POSITIVE LOGITS
     transcript
    1.77
     ahead
    1.45
    recht
    1.36
     archive
    1.36
     tax
    1.33
    opf
    1.32
     Editor
    1.30
     rebut
    1.30
     Tax
    1.29
     proteins
    1.29
    Activations Density 0.046%

    No Known Activations