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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13530
    Prev
    Next
    INDEX
    Explanations

    references to APIs and error handling in code or 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/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
    507
    +0.22
    1.3%
    263
    +0.14
    0.8%
    422
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.22
    0.07
    340
    +0.14
    0.09
    479
    +0.14
    0.05
    Negative Logits
    rapeut
    -1.87
    cyl
    -1.60
    hores
    -1.58
    soever
    -1.58
     excretion
    -1.49
    elves
    -1.44
     righteousness
    -1.43
    ymoon
    -1.43
     bladder
    -1.42
    uries
    -1.38
    POSITIVE LOGITS
    ĻĤ
    2.29
    ©
    2.27
    ¦
    2.16
    ¼
    2.15
    ¸
    2.08
    ļ
    2.05
    ³
    2.01
    §
    1.99
    ¤
    1.94
    ĩ
    1.94
    Activations Density 4.032%

    No Known Activations