© 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. 27895
    Prev
    Next
    INDEX
    Explanations

    keywords associated with foundational concepts and frameworks in various contexts

    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
    4
    +0.15
    0.8%
    23
    +0.13
    0.7%
    83
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.15
    0.04
    268
    +0.13
    0.04
    4
    +0.12
    0.04
    Negative Logits
    »¿
    -5.27
    -4.95
    ↵
    -4.95
    Â
    -4.95
    -4.95
    -4.95
    -4.95
    ↵
    -4.95
    č↵
    -4.95
    ↵↵
    -4.95
    POSITIVE LOGITS
     inert
    1.71
     oxid
    1.60
    entially
    1.59
     heterogeneous
    1.51
    utively
    1.48
     deleter
    1.47
    ogen
    1.46
    ostatic
    1.45
     conical
    1.44
     graded
    1.42
    Activations Density 0.418%

    No Known Activations