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. 26854
    Prev
    Next
    INDEX
    Explanations

    details about brand identity or branding practices

    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
    +0.24
    1.3%
    369
    +0.14
    0.8%
    225
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.24
    0.10
    369
    +0.14
    0.05
    88
    +0.12
    0.09
    Negative Logits
     sever
    -1.49
     ownership
    -1.39
    amente
    -1.35
    anted
    -1.33
     alike
    -1.31
     "-
    -1.30
    hee
    -1.29
    ÃĤ
    -1.27
    *"
    -1.26
    ystem
    -1.26
    POSITIVE LOGITS
    Errno
    1.46
    ttes
    1.42
     tonight
    1.41
    ings
    1.37
     yours
    1.34
     tomorrow
    1.32
    lights
    1.31
    orna
    1.29
     pretext
    1.28
    ismiss
    1.27
    Activations Density 9.490%

    No Known Activations