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. 26780
    Prev
    Next
    INDEX
    Explanations

    references to various configurations or settings within contexts

    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
    376
    +0.12
    0.7%
    227
    +0.12
    0.7%
    498
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.12
    0.03
    498
    +0.12
    0.02
    227
    +0.12
    0.02
    Negative Logits
    Ĵ
    -2.72
    §
    -2.69
    Ŀ
    -2.52
    ¿½
    -2.51
    Į
    -2.38
    Ī
    -2.35
    ĸ
    -2.34
    ľ
    -2.26
    ī
    -2.19
    İ
    -2.19
    POSITIVE LOGITS
     override
    1.82
    ulates
    1.68
    lies
    1.67
     forth
    1.67
    ton
    1.66
    ifies
    1.65
     fire
    1.61
     horizon
    1.59
     aside
    1.58
     dictate
    1.54
    Activations Density 0.127%

    No Known Activations