© 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. 1-RES-SM
    11. 25225
    Prev
    Next
    INDEX
    Explanations

    acronyms or shorthand terms related to organizations or technical specifications

    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
    369
    +0.21
    1.2%
    156
    +0.20
    1.2%
    410
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.21
    0.07
    410
    +0.20
    0.08
    129
    +0.18
    0.03
    Negative Logits
     others
    -1.65
    InstanceState
    -1.64
    sein
    -1.54
     elsewhere
    -1.52
    bes
    -1.46
     diseases
    -1.45
     extremities
    -1.44
    orems
    -1.44
    oscopy
    -1.42
     {}
    -1.42
    POSITIVE LOGITS
    ·
    2.17
    Ŀ
    2.05
    º
    2.03
    °
    1.97
    Ĩ
    1.94
    ļ
    1.91
    Ľ
    1.90
    Į
    1.87
    ®
    1.84
    ´
    1.83
    Activations Density 0.616%

    No Known Activations