© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26433
    Prev
    Next
    INDEX
    Explanations

    the version numbers of software licenses

    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
    371
    +0.12
    0.7%
    294
    +0.10
    0.6%
    220
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.12
    0.02
    116
    +0.10
    0.02
    222
    +0.10
    0.01
    Negative Logits
    ľĵ
    -4.08
    ↵
    -3.55
    -3.55
    -3.55
    ↵
    -3.55
    -3.55
    ↵
    -3.55
    -3.55
    č↵č↵
    -3.55
    ↵            ↵
    -3.55
    POSITIVE LOGITS
    holder
    1.51
    sible
    1.45
    pack
    1.43
    igned
    1.40
     option
    1.38
     revoked
    1.36
     assignment
    1.35
     waiver
    1.34
     issued
    1.32
    prot
    1.32
    Activations Density 0.106%

    No Known Activations