© 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. 1-RES-SM
    11. 30011
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic locations and areas

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.19
    1.1%
    110
    +0.18
    1.0%
    180
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.19
    0.02
    503
    +0.18
    0.01
    30
    +0.13
    0.02
    Negative Logits
     whistle
    -1.66
     morale
    -1.63
    iful
    -1.59
     gradual
    -1.59
     serious
    -1.59
     vigorous
    -1.58
    ying
    -1.57
    rogen
    -1.56
    athing
    -1.51
     vengeance
    -1.51
    POSITIVE LOGITS
    ¡
    2.39
    £
    2.28
    ĻĤ
    2.11
    ĸ
    2.07
    Ĺ
    2.06
     locations
    2.05
    Ń
    2.01
     location
    2.00
    ķ
    1.95
    ©
    1.93
    Activations Density 0.078%

    No Known Activations