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. 11606
    Prev
    Next
    INDEX
    Explanations

    combinations of punctuation marks and numbers

    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
    478
    +0.22
    1.3%
    23
    +0.15
    0.8%
    202
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.22
    0.03
    129
    +0.15
    0.01
    8
    +0.12
    0.03
    Negative Logits
    µ
    -2.42
    Ń
    -2.38
    Ģ
    -2.32
    ¼
    -2.24
    Ĵ
    -2.22
    ¬
    -2.22
    £
    -2.13
    ¥
    -2.08
    ł
    -2.05
    »¿
    -1.95
    POSITIVE LOGITS
     whole
    1.78
    -)
    1.73
     charset
    1.71
     convers
    1.67
     else
    1.65
     other
    1.63
     cf
    1.62
     others
    1.58
    woke
    1.55
    also
    1.53
    Activations Density 0.222%

    No Known Activations