© 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. 29851
    Prev
    Next
    INDEX
    Explanations

    references to places, specifically those associated with cultural or religious significance

    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
    271
    +0.24
    1.4%
    479
    +0.16
    0.9%
    261
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.24
    0.01
    111
    +0.16
    0.09
    156
    +0.14
    0.10
    Negative Logits
    atinib
    -1.64
    omore
    -1.40
    cos
    -1.34
    quito
    -1.33
    googleapis
    -1.33
    dtd
    -1.32
    crypt
    -1.32
    xsd
    -1.30
    hab
    -1.29
    met
    -1.29
    POSITIVE LOGITS
     Himself
    1.61
     spirits
    1.59
     knees
    1.54
     Writers
    1.48
     ankles
    1.48
    ίαÏĤ
    1.45
    ени
    1.43
    rano
    1.42
    ãĥ¥
    1.40
    ushing
    1.37
    Activations Density 1.299%

    No Known Activations