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. 26814
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "pond"

    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
    477
    +0.13
    0.7%
    410
    +0.12
    0.7%
    348
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.13
    0.02
    348
    +0.12
    0.02
    477
    +0.12
    0.02
    Negative Logits
    pers
    -1.58
    psin
    -1.55
     crate
    -1.50
    pher
    -1.48
    odic
    -1.45
     unrestricted
    -1.43
    ters
    -1.41
     dB
    -1.40
     limited
    -1.40
    pering
    -1.38
    POSITIVE LOGITS
    irectory
    1.78
    stown
    1.78
    heim
    1.77
    ency
    1.63
    iffe
    1.63
    ship
    1.62
    essa
    1.62
    essen
    1.59
    esa
    1.59
    own
    1.58
    Activations Density 0.095%

    No Known Activations