© 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. 29359
    Prev
    Next
    INDEX
    Explanations

    references to directional terms, particularly focusing on "north" and "south"

    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
    457
    +0.14
    0.8%
    326
    +0.12
    0.7%
    459
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.14
    0.02
    415
    +0.12
    0.01
    81
    +0.11
    0.01
    Negative Logits
    EventArgs
    -1.68
    SUCCESS
    -1.64
     counseling
    -1.62
    usions
    -1.60
    xygen
    -1.60
    Errors
    -1.53
    ailure
    -1.51
    Nothing
    -1.48
     fact
    -1.48
    ionage
    -1.47
    POSITIVE LOGITS
     west
    1.99
    strom
    1.97
     east
    1.87
     corridor
    1.85
    west
    1.83
    wick
    1.66
     aisle
    1.66
    ward
    1.63
    wards
    1.61
    dale
    1.60
    Activations Density 0.055%

    No Known Activations