© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28157
    Prev
    Next
    INDEX
    Explanations

    specific locations and addresses

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    17
    +0.18
    1.0%
    288
    +0.14
    0.8%
    34
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.18
    0.05
    288
    +0.14
    0.12
    17
    +0.11
    -0.03
    Negative Logits
    ulses
    -1.67
    PtrFromString
    -1.57
    acity
    -1.56
    claim
    -1.55
    ils
    -1.53
     sudden
    -1.53
    creation
    -1.50
    cknowled
    -1.49
    abilities
    -1.49
    ...](
    -1.47
    POSITIVE LOGITS
     broch
    1.57
     nowhere
    1.56
     housing
    1.56
     locations
    1.55
     Plaza
    1.54
     downtown
    1.51
     Walmart
    1.50
    ij
    1.50
     Theater
    1.47
     headquarters
    1.46
    Activations Density 4.568%

    No Known Activations