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. 29588
    Prev
    Next
    INDEX
    Explanations

    terms related to automation and automated processes

    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
    156
    +0.14
    0.8%
    148
    +0.13
    0.7%
    405
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.14
    0.01
    90
    +0.13
    0.02
    112
    +0.13
    0.01
    Negative Logits
    ful
    -1.88
     elsewhere
    -1.49
    heastern
    -1.48
    enth
    -1.46
    place
    -1.45
    weg
    -1.42
    ulf
    -1.41
    au
    -1.40
    à±ģ
    -1.39
     proposition
    -1.39
    POSITIVE LOGITS
     registration
    1.89
     transmission
    1.68
    encoder
    1.45
     Transmission
    1.40
     timer
    1.40
     transmissions
    1.39
     "%
    1.38
     reload
    1.37
     roll
    1.36
     shutter
    1.34
    Activations Density 0.106%

    No Known Activations