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. 27052
    Prev
    Next
    INDEX
    Explanations

    references to information and data structures, particularly dictionary-like terms

    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
    410
    +0.15
    0.9%
    434
    +0.14
    0.8%
    158
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.15
    0.03
    503
    +0.14
    0.01
    379
    +0.12
    0.02
    Negative Logits
     particular
    -1.60
     careful
    -1.59
    *](#
    -1.52
    '?"
    -1.50
    "){
    -1.47
     earth
    -1.44
    ocrine
    -1.42
    grades
    -1.42
     continuous
    -1.40
     *_
    -1.39
    POSITIVE LOGITS
    ŀ
    3.75
    Ń
    3.52
    Ĵ
    3.37
    £
    3.35
    ĩ
    3.28
    IJ
    3.25
    İ
    3.24
    ¥
    3.24
    ģ
    3.19
    Ŀ
    3.17
    Activations Density 0.191%

    No Known Activations