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. 26948
    Prev
    Next
    INDEX
    Explanations

    sentences that convey a sense of finality or conclusion

    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
    476
    +0.12
    0.7%
    328
    +0.12
    0.7%
    292
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.14
    156
    +0.12
    0.06
    271
    +0.12
    0.07
    Negative Logits
    ·¸
    -1.68
    ĥ½
    -1.66
    ³
    -1.60
    ¨
    -1.52
    unto
    -1.50
    onin
    -1.49
    ozo
    -1.48
    µ
    -1.48
    §
    -1.47
    {})
    -1.42
    POSITIVE LOGITS
    adays
    1.59
    itary
    1.55
     mind
    1.52
     try
    1.45
    twitter
    1.38
     afternoon
    1.34
     nap
    1.33
     chant
    1.33
     contrary
    1.33
     maybe
    1.32
    Activations Density 0.055%

    No Known Activations