© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28531
    Prev
    Next
    INDEX
    Explanations

    the use of adverbs and phrases that characterize frequency or manner in a context

    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
    153
    +0.14
    0.8%
    248
    +0.13
    0.7%
    419
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.14
    0.09
    248
    +0.13
    0.09
    219
    +0.12
    0.08
    Negative Logits
    ôle
    -1.44
     sit
    -1.40
    acker
    -1.36
    elle
    -1.35
    uto
    -1.35
     {
    -1.33
    meet
    -1.31
    ari
    -1.30
    noreply
    -1.28
    ette
    -1.27
    POSITIVE LOGITS
     ↵
    2.79
    <|padding|>
    2.79
     ↵
    2.79
    <|outofrange|>
    2.79
    ↵
    2.79
    ↵
    2.79
    č↵
    2.79
    2.79
    ↵
    2.79
    2.79
    Activations Density 1.405%

    No Known Activations