© 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. 25862
    Prev
    Next
    INDEX
    Explanations

    terms related to technical support and documentation

    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
    189
    +0.17
    0.9%
    419
    +0.14
    0.8%
    438
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.04
    271
    +0.14
    0.01
    156
    +0.12
    0.02
    Negative Logits
     Islands
    -1.45
    Č
    -1.42
    hores
    -1.42
     chance
    -1.39
    heit
    -1.39
    à±ģ
    -1.38
     [@
    -1.37
    apine
    -1.36
    ctic
    -1.36
    à±į
    -1.35
    POSITIVE LOGITS
    ĵ
    1.86
    ģ
    1.79
    »¿
    1.77
    umen
    1.72
    ĻĤ
    1.69
    ĭ
    1.68
    Ĩ
    1.66
    Ĺ
    1.58
    ĸ´
    1.56
    ĸ
    1.55
    Activations Density 0.118%

    No Known Activations