Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 28703
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to biological and medical processes

    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
    248
    +0.20
    1.1%
    98
    +0.17
    1.0%
    489
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.59
    156
    +0.17
    0.54
    71
    +0.13
    0.52
    Negative Logits
    Ļª
    -2.98
    ©
    -2.72
    ľĵ
    -2.56
    ¾
    -2.53
    ²
    -2.53
    £
    -2.48
    ĻĤ
    -2.46
    ŀ
    -2.44
    ³
    -2.41
    ¿
    -2.39
    POSITIVE LOGITS
    pez
    1.95
    odend
    1.73
    Fig
    1.67
     case
    1.45
     population
    1.43
    ait
    1.42
     ^[@
    1.42
     conducting
    1.42
     ================================================================
    1.41
    Figs
    1.38
    Activations Density 3.722%

    No Known Activations