© 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. 4-RES-SM
    11. 14271
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers, particularly related to individuals, organizations, or brands

    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
    175
    +0.16
    0.9%
    499
    +0.13
    0.7%
    356
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.16
    0.02
    340
    +0.13
    0.02
    497
    +0.13
    0.01
    Negative Logits
     Twin
    -1.85
     McConnell
    -1.66
     Zel
    -1.43
    chen
    -1.43
     quo
    -1.42
     doct
    -1.40
     Kl
    -1.38
     PN
    -1.33
     Sn
    -1.32
    ibe
    -1.32
    POSITIVE LOGITS
     Ar
    3.86
    Ar
    3.46
     ar
    3.11
     AR
    3.08
    ar
    2.81
    AR
    2.81
     Archer
    2.72
    arb
    2.44
     Ark
    2.43
    ARR
    2.33
    Activations Density 0.873%

    No Known Activations