© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10905
    Prev
    Next
    INDEX
    Explanations

    expressions of vulnerability and resilience

    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
    369
    +0.16
    0.9%
    263
    +0.14
    0.8%
    161
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.16
    0.09
    320
    +0.14
    0.10
    56
    +0.13
    -0.03
    Negative Logits
    aliana
    -1.73
    una
    -1.60
    ^](#
    -1.49
     Manual
    -1.46
     annotated
    -1.46
    .*]{}
    -1.43
     vein
    -1.41
    .+
    -1.38
    impl
    -1.37
    }}$-
    -1.37
    POSITIVE LOGITS
     expires
    1.54
    pires
    1.45
     stops
    1.42
    thirds
    1.37
    herry
    1.35
    ricanes
    1.35
    ynes
    1.27
     Appeal
    1.27
     circumstances
    1.26
     stopped
    1.24
    Activations Density 2.780%

    No Known Activations