© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27177
    Prev
    Next
    INDEX
    Explanations

    instances of the word "modified" and variations related to changes or alterations

    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
    156
    +0.25
    1.4%
    340
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.25
    0.01
    340
    +0.12
    0.02
    493
    +0.12
    0.02
    Negative Logits
    west
    -1.74
    leen
    -1.69
    les
    -1.64
    fire
    -1.58
    iest
    -1.50
    ksen
    -1.47
    ighter
    -1.47
    llo
    -1.41
    li
    -1.40
    ney
    -1.39
    POSITIVE LOGITS
     form
    1.68
     ones
    1.64
     versions
    1.62
     BSD
    1.59
    iator
    1.49
     forms
    1.47
     thereto
    1.45
    plify
    1.43
     from
    1.43
     existing
    1.40
    Activations Density 0.095%

    No Known Activations