© 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. 13180
    Prev
    Next
    INDEX
    Explanations

    references to flags and their associated values in various contexts

    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
    +0.18
    1.0%
    354
    +0.15
    0.8%
    122
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.18
    0.02
    443
    +0.15
    0.01
    467
    +0.12
    0.01
    Negative Logits
    TRODUCTION
    -1.58
     conne
    -1.41
     relation
    -1.39
     relationship
    -1.39
     acquaintance
    -1.37
     asleep
    -1.37
    dule
    -1.36
     prospective
    -1.33
     vivo
    -1.33
     calm
    -1.32
    POSITIVE LOGITS
    ellate
    2.26
    ellation
    2.24
    pole
    2.04
    stones
    1.96
    ged
    1.93
    ellar
    1.84
    staff
    1.77
    ellants
    1.77
    stone
    1.76
     icon
    1.63
    Activations Density 0.160%

    No Known Activations