© 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 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. 28859
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and software development

    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
    +0.17
    1.0%
    153
    +0.14
    0.8%
    122
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.17
    -0.03
    116
    +0.14
    0.07
    122
    +0.13
    0.08
    Negative Logits
     poles
    -1.51
    ply
    -1.34
     gar
    -1.32
     hybrids
    -1.30
     duty
    -1.28
     cured
    -1.27
     riding
    -1.26
     mammary
    -1.26
    ported
    -1.25
     hon
    -1.25
    POSITIVE LOGITS
    "}](#
    1.95
    à±į
    1.94
    à«ĩ
    1.88
    à°¿
    1.81
    à¯į
    1.80
    ]:
    1.67
     */,
    1.66
    áĢº
    1.62
    ennes
    1.62
    à©
    1.58
    Activations Density 3.617%

    No Known Activations