© 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. 12624
    Prev
    Next
    INDEX
    Explanations

    references to brands and product categories in a consumer context

    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
    482
    +0.14
    0.8%
    279
    +0.13
    0.8%
    77
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.14
    0.05
    345
    +0.13
    0.12
    77
    +0.12
    0.06
    Negative Logits
    reon
    -1.51
    hover
    -1.35
    named
    -1.34
    Expected
    -1.34
    '))
    -1.33
    overflow
    -1.33
    cyst
    -1.31
    respectively
    -1.30
    Figures
    -1.30
    ulp
    -1.30
    POSITIVE LOGITS
    Ļ
    1.91
    Ł
    1.77
    ITED
    1.73
    ³
    1.72
    ĺ
    1.66
    ª
    1.64
    ĵ
    1.58
    Ķ
    1.58
    ł
    1.58
    ¤
    1.57
    Activations Density 2.519%

    No Known Activations