© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28418
    Prev
    Next
    INDEX
    Explanations

    phrases related to definitions and clarifications of concepts

    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
    161
    +0.15
    0.9%
    145
    +0.12
    0.7%
    44
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.05
    243
    +0.12
    0.08
    379
    +0.12
    0.08
    Negative Logits
    ĻĤ
    -4.14
    Ļª
    -3.83
    Ĥ¬
    -3.70
    İ
    -3.66
    ¸
    -3.56
    IJ
    -3.45
    ©
    -3.35
    ¼
    -3.30
    ĥ
    -3.26
    ħ
    -3.22
    POSITIVE LOGITS
     yours
    1.56
     crap
    1.55
     essence
    1.50
     gotta
    1.50
     okay
    1.47
     FITNESS
    1.46
     theirs
    1.46
    cle
    1.41
     vibe
    1.40
     bottom
    1.39
    Activations Density 1.112%

    No Known Activations