© 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. 1-RES-SM
    6. 26670
    Prev
    Next
    INDEX
    Explanations

    references to licensing documentation

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    401
    +0.13
    0.8%
    320
    +0.13
    0.8%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.13
    0.02
    192
    +0.13
    0.02
    273
    +0.12
    0.01
    Negative Logits
    ...](
    -1.69
     predicting
    -1.63
     Month
    -1.60
     detecting
    -1.53
    UES
    -1.51
    atching
    -1.47
    ](
    -1.37
     diagnosing
    -1.36
    ORN
    -1.35
     assessing
    -1.34
    POSITIVE LOGITS
    javase
    1.62
    º
    1.55
    liche
    1.53
     prá
    1.49
    AndroidRuntime
    1.46
     hospitality
    1.45
     pasta
    1.44
    algebras
    1.39
    appeal
    1.34
     tast
    1.33
    Activations Density 0.069%

    No Known Activations