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. 11518
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    482
    +0.11
    0.7%
    105
    +0.11
    0.6%
    433
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.11
    0.02
    482
    +0.11
    0.02
    318
    +0.10
    0.01
    Negative Logits
    ¼
    -1.64
    coins
    -1.58
     deserve
    -1.55
    ®
    -1.54
     scenes
    -1.50
    rene
    -1.49
    ose
    -1.46
    ris
    -1.39
    are
    -1.39
     yourself
    -1.39
    POSITIVE LOGITS
    Docket
    1.70
    debted
    1.31
    ogy
    1.30
     Bd
    1.30
    zt
    1.28
    åĬ¡
    1.27
    YPT
    1.25
    enix
    1.25
    jq
    1.25
     911
    1.25
    Activations Density 0.029%

    No Known Activations