© 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. 4-RES-SM
    11. 11317
    Prev
    Next
    INDEX
    Explanations

    references to licenses and copyright information

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    156
    +0.24
    1.4%
    307
    +0.16
    0.9%
    21
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.24
    0.04
    213
    +0.16
    0.05
    333
    +0.14
    0.04
    Negative Logits
     population
    -1.50
    isine
    -1.48
     troops
    -1.44
    aukee
    -1.43
    stown
    -1.41
    <|outofrange|>
    -1.39
    <|outofrange|>
    -1.39
    ↵↵↵
    -1.39
    -1.39
    -1.39
    POSITIVE LOGITS
     GPL
    2.62
    GPL
    2.40
     LICENSE
    2.28
     BSD
    2.24
    LICENSE
    2.06
    mozilla
    2.05
    GNU
    1.98
     COPYRIGHT
    1.95
    bsd
    1.94
    copyright
    1.94
    Activations Density 0.438%

    No Known Activations