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

    Neuronpedia

    Jacobian LensNEW
    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. 10436
    Prev
    Next
    INDEX
    Explanations

    various options and choices available in different 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/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
    156
    +0.15
    0.9%
    287
    +0.14
    0.8%
    217
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.15
    0.04
    172
    +0.14
    0.02
    433
    +0.13
    0.02
    Negative Logits
    »¿
    -3.00
    ĻĤ
    -2.65
    ĥ½
    -2.64
    ĵ
    -2.34
    ľĵ
    -2.31
    Ļª
    -2.26
    ĥ
    -2.25
    ľ
    -2.21
    Ł
    -2.12
    Ĵ
    -2.12
    POSITIVE LOGITS
     choices
    2.25
     available
    2.12
     options
    2.02
     set
    1.79
     adjustable
    1.79
     removable
    1.78
     panel
    1.69
     choice
    1.67
     reserved
    1.63
     seating
    1.59
    Activations Density 0.125%

    No Known Activations