© 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. 24448
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to dropping off items or people

    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
    59
    +0.17
    1.0%
    376
    +0.15
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.17
    0.03
    162
    +0.15
    0.02
    164
    +0.13
    0.02
    Negative Logits
    ĥ½
    -2.82
    ķ
    -2.51
    ĸ´
    -2.49
    į
    -2.47
    Īĺ
    -2.43
    ĺ
    -2.40
    Į
    -2.38
    Ĺ
    -2.38
     ↵
    -2.33
    ↵
    -2.33
    POSITIVE LOGITS
    outs
    1.98
     below
    1.84
    point
    1.76
    starter
    1.73
     down
    1.73
    zone
    1.72
     apart
    1.70
    [-
    1.69
    points
    1.67
     zone
    1.66
    Activations Density 0.095%

    No Known Activations