© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12293
    Prev
    Next
    INDEX
    Explanations

    terms related to places and buildings

    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
    25
    +0.19
    1.1%
    194
    +0.13
    0.7%
    205
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.19
    0.09
    368
    +0.13
    0.04
    179
    +0.10
    0.09
    Negative Logits
    -7.10
    ↵
    -7.10
     ↵
    -7.10
    ↵↵↵
    -7.10
    ↵
    -7.10
    ↵
    -7.10
    -7.10
    ↵
    -7.10
     ↵
    -7.10
    č↵
    -7.10
    POSITIVE LOGITS
     located
    2.92
     overlooking
    2.89
     situated
    2.80
     erected
    2.68
     downtown
    2.62
     adjoining
    2.60
    yard
    2.56
     renovation
    2.53
    keeper
    2.47
     nearby
    2.45
    Activations Density 1.260%

    No Known Activations