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. 11579
    Prev
    Next
    INDEX
    Explanations

    activities related to goal setting and personal development

    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
    376
    +0.15
    0.8%
    457
    +0.13
    0.7%
    465
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.15
    0.07
    376
    +0.13
    0.03
    470
    +0.11
    0.08
    Negative Logits
    ľ
    -3.95
    §
    -3.94
    Ł
    -3.74
    Ĵ
    -3.61
    ģ
    -3.61
    ī
    -3.59
    ¨
    -3.58
    Ľ
    -3.54
    ¥
    -3.45
    ¾
    -3.40
    POSITIVE LOGITS
    ulate
    2.04
    redients
    1.90
    pone
    1.74
    emente
    1.72
    selves
    1.70
    ton
    1.67
    stitute
    1.63
     minds
    1.62
     exercises
    1.61
     lessons
    1.57
    Activations Density 0.860%

    No Known Activations