© 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. 13558
    Prev
    Next
    INDEX
    Explanations

    references to programming and APIs

    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
    502
    +0.13
    0.7%
    192
    +0.12
    0.7%
    371
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.13
    0.04
    361
    +0.12
    0.04
    77
    +0.11
    0.01
    Negative Logits
    ı
    -3.43
    §
    -3.10
    ¼
    -3.06
    ¿½
    -2.99
    č↵
    -2.93
    -2.93
               ↵
    -2.93
    -2.93
    ↵
    -2.93
    <|outofrange|>
    -2.93
    POSITIVE LOGITS
    mith
    2.71
    heet
    2.57
    creen
    2.49
    olver
    2.44
    helf
    2.33
    erver
    2.32
    ource
    2.25
    olute
    2.22
    urface
    2.19
    CRIPT
    2.17
    Activations Density 0.337%

    No Known Activations