© 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. 30407
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial proceedings

    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
    102
    +0.14
    0.8%
    38
    +0.13
    0.7%
    441
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.14
    0.04
    399
    +0.13
    0.06
    38
    +0.13
    0.07
    Negative Logits
     $%
    -1.43
     Called
    -1.29
     Born
    -1.24
     Redist
    -1.23
     abbreviated
    -1.22
    named
    -1.21
    brev
    -1.20
    operated
    -1.18
     advertising
    -1.16
    Affirmed
    -1.15
    POSITIVE LOGITS
    ŀ
    2.57
    ļ
    2.56
    ·¸
    2.51
    Ļ
    2.48
    ³
    2.45
    ¹
    2.44
    ↵
    2.43
     ↵
    2.43
    <|outofrange|>
    2.43
    ↵            ↵
    2.43
    Activations Density 2.573%

    No Known Activations