© 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. 10006
    Prev
    Next
    INDEX
    Explanations

    concepts related to time sensitivity and efficiency issues

    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
    263
    +0.20
    1.2%
    141
    +0.15
    0.9%
    153
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.20
    0.09
    141
    +0.15
    0.06
    161
    +0.14
    0.03
    Negative Logits
    ³
    -3.17
    ¶
    -3.05
    ¼
    -3.01
    ĩ
    -2.99
    į
    -2.89
    ½
    -2.76
    ¦
    -2.75
    Ń
    -2.73
    ħ
    -2.73
    «
    -2.71
    POSITIVE LOGITS
    ...)
    2.05
    `)
    1.87
    !)
    1.76
    })$$
    1.74
    ')
    1.72
    .)
    1.68
    ?)
    1.65
    *)
    1.60
    }$)
    1.59
    hin
    1.54
    Activations Density 1.327%

    No Known Activations