Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26784
    Prev
    Next
    INDEX
    Explanations

    references to strenuous effort or difficulty

    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
    452
    +0.14
    0.8%
    82
    +0.12
    0.7%
    454
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.14
    0.05
    82
    +0.12
    0.04
    99
    +0.11
    0.04
    Negative Logits
    ľ
    -1.87
    ¡
    -1.84
    ¦
    -1.71
    §
    -1.68
    ¢
    -1.67
    gmail
    -1.64
    ¨
    -1.61
     entirety
    -1.61
    ĵ
    -1.60
    Ń
    -1.59
    POSITIVE LOGITS
    ened
    2.08
    ening
    1.86
    eners
    1.84
    hart
    1.70
    ties
    1.68
    esy
    1.66
    coded
    1.62
    bound
    1.61
    cover
    1.60
    iness
    1.60
    Activations Density 0.076%

    No Known Activations