© 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. 4-RES-SM
    11. 11330
    Prev
    Next
    INDEX
    Explanations

    references to user interface components and their interactions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.18
    1.0%
    156
    +0.14
    0.8%
    255
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.18
    0.14
    255
    +0.14
    0.00
    260
    +0.11
    0.13
    Negative Logits
    ĥ½
    -4.18
    ↵
    -4.00
    č↵
    -4.00
    ↵
    -4.00
    -4.00
    ↵    ↵
    -4.00
    ↵↵
    -4.00
    ↵
    -4.00
    ↵
    -4.00
    ↵  âĢĥ
    -4.00
    POSITIVE LOGITS
    ();
    2.61
    ()
    2.46
    AtIndex
    2.45
    (()
    2.44
    (){
    2.42
    ():
    2.32
    ().
    2.21
    (_
    2.14
    ($_
    2.08
    ([]
    2.04
    Activations Density 1.328%

    No Known Activations