© 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. 13284
    Prev
    Next
    INDEX
    Explanations

    terms related to pricing and financial aspects

    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
    372
    +0.14
    0.8%
    213
    +0.12
    0.6%
    203
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.02
    391
    +0.12
    0.03
    372
    +0.11
    0.02
    Negative Logits
    wards
    -1.52
     gonna
    -1.48
    grass
    -1.46
     awake
    -1.44
    ../../
    -1.44
     simulated
    -1.44
     Dil
    -1.40
    jam
    -1.39
     called
    -1.37
     Morning
    -1.37
    POSITIVE LOGITS
    ŀ
    3.19
    ¢
    3.07
    ©
    3.06
    ¡
    3.04
    Ĵ
    2.95
    Ĭ
    2.93
    £
    2.89
    §
    2.88
    ·
    2.82
    IJ
    2.72
    Activations Density 0.302%

    No Known Activations