© 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. 31715
    Prev
    Next
    INDEX
    Explanations

    references to wiki pages and related commands or syntax

    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
    23
    +0.15
    0.9%
    320
    +0.13
    0.7%
    153
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.15
    0.05
    433
    +0.13
    0.04
    373
    +0.13
    0.06
    Negative Logits
    ©
    -2.31
    ĻĤ
    -2.20
    Ļª
    -2.18
    IJ
    -2.13
    Ĵ
    -2.07
    £
    -2.07
    ĨĴ
    -2.04
    ľĵ
    -1.96
    ±
    -1.92
    ¤
    -1.85
    POSITIVE LOGITS
    à±ģ
    1.79
    ÑģÑĤво
    1.52
    iya
    1.50
    erved
    1.44
    ometry
    1.43
    ionine
    1.37
    icity
    1.36
    ????
    1.33
    otransferase
    1.31
    оÑģ
    1.28
    Activations Density 3.612%

    No Known Activations