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. 2-RES-SM
    6. 29253
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts and errors

    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
    72
    +0.19
    1.1%
    436
    +0.15
    0.9%
    369
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.19
    0.06
    416
    +0.15
    0.06
    262
    +0.15
    0.05
    Negative Logits
     called
    -1.51
     held
    -1.47
    aws
    -1.38
     moth
    -1.37
    chos
    -1.37
     needed
    -1.34
     includes
    -1.34
     Canadians
    -1.32
     susp
    -1.30
     equipped
    -1.30
    POSITIVE LOGITS
    amente
    1.71
     Discussion
    1.51
    (@
    1.50
    igent
    1.44
     (@
    1.44
    issance
    1.40
     lane
    1.40
    Ĵ
    1.38
    wikipedia
    1.37
     Rehabilitation
    1.36
    Activations Density 1.229%

    No Known Activations