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. 2-RES-SM
    6. 29391
    Prev
    Next
    INDEX
    Explanations

    customizable content related to research and information dissemination

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    342
    +0.13
    0.8%
    213
    +0.12
    0.7%
    167
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.13
    0.07
    453
    +0.12
    0.09
    342
    +0.12
    0.06
    Negative Logits
    Ļª
    -2.70
    ĨĴ
    -2.39
    ĻĤ
    -2.33
    ŀ
    -2.31
    Ĺ
    -2.20
    ģ
    -2.12
    ĸ
    -2.08
    ¿½
    -2.08
    à±į
    -2.05
    º
    -2.04
    POSITIVE LOGITS
    NON
    1.50
     briefs
    1.48
    igned
    1.42
     collectors
    1.41
     billing
    1.38
     validity
    1.38
     dated
    1.34
    Argued
    1.34
    gage
    1.33
     2017
    1.32
    Activations Density 3.595%

    No Known Activations