© 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. 28270
    Prev
    Next
    INDEX
    Explanations

    elements related to personal stories or narratives of individuals

    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
    176
    +0.15
    0.9%
    56
    +0.14
    0.8%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.15
    -0.05
    176
    +0.14
    0.12
    23
    +0.13
    0.15
    Negative Logits
    Ļª
    -2.08
    ©
    -1.94
    ¦
    -1.89
    Į
    -1.83
    Ĥ¬
    -1.70
    IJ
    -1.68
    ľĵ
    -1.66
    ĩ
    -1.64
    ģ
    -1.64
    ª
    -1.64
    POSITIVE LOGITS
    '))
    1.42
     heck
    1.42
     starving
    1.38
     Resistance
    1.33
     hell
    1.29
     grub
    1.28
    olate
    1.27
     bott
    1.26
     grazing
    1.25
     squat
    1.25
    Activations Density 3.779%

    No Known Activations