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. 29403
    Prev
    Next
    INDEX
    Explanations

    structured data or file paths in a programming or technical context

    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
    217
    +0.18
    1.0%
    369
    +0.13
    0.7%
    17
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.18
    0.17
    17
    +0.13
    0.03
    143
    +0.13
    0.10
    Negative Logits
    ictions
    -1.73
    )]{}
    -1.67
    alam
    -1.65
     [â̦]
    -1.54
    .\[[@
    -1.53
    )\]
    -1.51
     (“
    -1.50
     “
    -1.47
    ,\[
    -1.47
    ,)
    -1.47
    POSITIVE LOGITS
     lovers
    1.45
     generals
    1.38
    weed
    1.34
    Gray
    1.31
    ---|---|---
    1.26
    '?"
    1.24
    '?
    1.24
    '
    1.23
    pound
    1.22
    crystall
    1.21
    Activations Density 2.268%

    No Known Activations