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. 26912
    Prev
    Next
    INDEX
    Explanations

    terms related to polymers and their properties

    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
    156
    +0.25
    1.5%
    71
    +0.10
    0.6%
    502
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.25
    0.01
    173
    +0.10
    0.01
    152
    +0.10
    0.01
    Negative Logits
    woke
    -2.23
     slightest
    -1.88
     latitude
    -1.53
    ogene
    -1.52
     difference
    -1.50
    rina
    -1.50
     vez
    -1.50
     fierc
    -1.49
     wait
    -1.48
    rians
    -1.47
    POSITIVE LOGITS
    isation
    2.01
    izations
    1.94
    ics
    1.81
    ization
    1.76
    izable
    1.67
    chain
    1.66
    cation
    1.66
    forcement
    1.64
    works
    1.61
    aments
    1.59
    Activations Density 0.039%

    No Known Activations