© 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. 1-RES-SM
    11. 26272
    Prev
    Next
    INDEX
    Explanations

    verbs indicating past or ongoing actions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    500
    +0.12
    0.7%
    202
    +0.12
    0.6%
    316
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.12
    0.02
    142
    +0.12
    0.01
    331
    +0.10
    0.02
    Negative Logits
    ?>
    -1.97
     Together
    -1.69
    Bag
    -1.65
    ercul
    -1.63
     Forward
    -1.59
     Clause
    -1.59
     handy
    -1.57
    weed
    -1.53
    together
    -1.50
     Header
    -1.48
    POSITIVE LOGITS
    oded
    1.84
    oding
    1.79
    ode
    1.59
    ³
    1.56
    odes
    1.55
    ¸
    1.54
    asing
    1.54
    uds
    1.52
    ģ
    1.51
    ĥ½
    1.49
    Activations Density 0.152%

    No Known Activations