© 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. 1-RES-SM
    11. 29293
    Prev
    Next
    INDEX
    Explanations

    mentions of internships and related terms

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    250
    +0.14
    0.8%
    177
    +0.13
    0.7%
    343
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.06
    156
    +0.13
    0.04
    271
    +0.11
    0.02
    Negative Logits
    ÑĤÑĮ
    -1.73
     integrity
    -1.68
    psis
    -1.65
    illance
    -1.64
    Į
    -1.60
    apine
    -1.55
    ľ
    -1.54
     ransom
    -1.53
     inheritance
    -1.52
     worms
    -1.49
    POSITIVE LOGITS
    acional
    2.51
    ship
    2.38
    ships
    2.35
    umerable
    1.82
    ermost
    1.79
    ode
    1.74
    stage
    1.70
    ationally
    1.64
    als
    1.61
    iero
    1.61
    Activations Density 0.339%

    No Known Activations