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. 26766
    Prev
    Next
    INDEX
    Explanations

    references to prohibitions or restrictions

    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
    264
    +0.15
    0.8%
    2
    +0.13
    0.7%
    425
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.15
    0.03
    425
    +0.13
    0.03
    2
    +0.12
    0.02
    Negative Logits
     totality
    -1.93
     recap
    -1.54
     retrospect
    -1.44
     rest
    -1.40
     forecast
    -1.39
    ometh
    -1.34
     close
    -1.34
    undry
    -1.33
    AMPLE
    -1.32
     divers
    -1.31
    POSITIVE LOGITS
    ishment
    2.20
    ishing
    1.99
    anas
    1.88
    amycin
    1.85
    quet
    1.78
    isher
    1.72
    bsd
    1.72
    ishers
    1.69
    jos
    1.68
    ivirus
    1.64
    Activations Density 0.160%

    No Known Activations