© 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. 1-RES-SM
    11. 24698
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or entity related to "El."

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.20
    1.2%
    410
    +0.17
    1.0%
    59
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.20
    0.03
    410
    +0.17
    0.03
    331
    +0.13
    0.03
    Negative Logits
    olar
    -1.63
    ettings
    -1.62
     laundering
    -1.59
     false
    -1.58
    '?"
    -1.55
    olation
    -1.46
    rbrace
    -1.45
    aturday
    -1.44
    hire
    -1.43
    usterity
    -1.43
    POSITIVE LOGITS
    º
    2.96
    ¦
    2.83
    Ĵ
    2.73
    ¡
    2.67
    Ľ
    2.65
    ł
    2.64
    ©
    2.63
    £
    2.53
    ¯
    2.51
    ĻĤ
    2.51
    Activations Density 0.062%

    No Known Activations