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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11375
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives describing size or scale

    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
    170
    +0.15
    0.9%
    465
    +0.14
    0.8%
    118
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.15
    0.07
    118
    +0.14
    0.06
    206
    +0.13
    0.03
    Negative Logits
    sets
    -1.58
    set
    -1.52
    stitution
    -1.47
    more
    -1.46
    ctor
    -1.45
     sein
    -1.43
    lement
    -1.42
    sev
    -1.41
    mentation
    -1.41
    psilon
    -1.37
    POSITIVE LOGITS
     ones
    1.73
     possible
    1.69
    afa
    1.67
    mouth
    1.63
     worldwide
    1.62
     conceivable
    1.45
    apest
    1.44
     ever
    1.44
    agh
    1.38
     interests
    1.36
    Activations Density 0.234%

    No Known Activations