© 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. 14486
    Prev
    Next
    INDEX
    Explanations

    phrases related to climbing and outdoor activities

    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
    307
    +0.13
    0.7%
    329
    +0.13
    0.7%
    268
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.13
    0.03
    30
    +0.13
    0.01
    311
    +0.13
    0.06
    Negative Logits
    ·¸
    -3.43
    Ħ
    -3.41
    ŀ
    -3.33
    ķ
    -3.30
    ģ
    -3.29
    °
    -3.26
    Ļ
    -3.23
    ĥ½
    -3.16
    ¢
    -3.14
    ¼
    -3.11
    POSITIVE LOGITS
     mountain
    3.71
     hiking
    3.65
     glac
    3.65
     clim
    3.50
     skiing
    3.49
     mountains
    3.42
     hike
    3.42
     ski
    3.34
     snow
    3.32
     Mountain
    3.31
    Activations Density 2.540%

    No Known Activations