© 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. 27377
    Prev
    Next
    INDEX
    Explanations

    identifiers and keywords 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
    185
    +0.11
    0.6%
    489
    +0.10
    0.5%
    48
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.11
    0.10
    298
    +0.10
    0.09
    185
    +0.10
    0.06
    Negative Logits
    respectively
    -1.70
     circulation
    -1.52
    quartile
    -1.40
    peritoneal
    -1.32
    she
    -1.32
    .]{}
    -1.31
    }$\
    -1.29
    ).](
    -1.28
    )].
    -1.28
     underground
    -1.28
    POSITIVE LOGITS
    APTER
    1.77
     Driver
    1.47
    ossier
    1.46
    еÐ
    1.44
    ling
    1.44
    wered
    1.43
     Course
    1.39
    оÐ
    1.38
    ils
    1.37
    akov
    1.35
    Activations Density 0.994%

    No Known Activations