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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11376
    Prev
    Next
    INDEX
    Explanations

    queries related to finding housing or rental opportunities

    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
    186
    +0.17
    1.0%
    167
    +0.14
    0.8%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.17
    0.12
    384
    +0.14
    0.06
    186
    +0.13
    0.05
    Negative Logits
    ¯
    -2.05
    Ĭ
    -1.80
    hift
    -1.72
     culmin
    -1.71
    Ł
    -1.64
    together
    -1.58
    Ĺ
    -1.56
    ĨĴ
    -1.56
     encompassing
    -1.55
    Īĺ
    -1.54
    POSITIVE LOGITS
     borrow
    1.61
    buy
    1.55
     graduate
    1.53
     college
    1.47
    achus
    1.38
     credit
    1.37
     dealer
    1.36
    eLife
    1.34
     commits
    1.33
    bid
    1.32
    Activations Density 2.397%

    No Known Activations