© 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. 2-RES-SM
    11. 11212
    Prev
    Next
    INDEX
    Explanations

    references to quantities or time periods

    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
    42
    +0.13
    0.7%
    460
    +0.13
    0.7%
    225
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.13
    0.05
    42
    +0.13
    0.04
    477
    +0.12
    0.05
    Negative Logits
    Ļª
    -3.47
    Į
    -3.43
    ľĵ
    -3.34
    ©
    -3.34
    ¯
    -3.34
    Ĥ
    -3.29
    §
    -3.22
    ·
    -3.21
    ĥ
    -3.17
    ³
    -3.14
    POSITIVE LOGITS
     years
    1.87
     seasons
    1.84
     chapters
    1.79
    innings
    1.73
     decades
    1.73
     thousand
    1.66
    century
    1.63
    eting
    1.60
    een
    1.58
     paragraphs
    1.55
    Activations Density 0.448%

    No Known Activations