© 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. 1-RES-SM
    11. 27748
    Prev
    Next
    INDEX
    Explanations

    specific details and entities, particularly names, dates, locations, and numerical values

    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
    23
    +0.18
    1.0%
    121
    +0.12
    0.7%
    66
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.18
    0.10
    121
    +0.12
    0.10
    481
    +0.12
    0.06
    Negative Logits
    ®
    -3.40
    ļ
    -3.12
    Ģ
    -3.00
    °
    -2.75
    ł
    -2.71
    ľĵ
    -2.71
    ĸ
    -2.64
    ħ
    -2.62
    ½
    -2.59
    ķ
    -2.57
    POSITIVE LOGITS
    ]>
    1.55
    seeing
    1.47
    coming
    1.46
     haste
    1.44
     About
    1.42
     thou
    1.42
     Eyes
    1.36
     blacks
    1.34
    >`
    1.34
    fered
    1.33
    Activations Density 2.759%

    No Known Activations