© 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. 30535
    Prev
    Next
    INDEX
    Explanations

    references to recipients or individuals related to information or 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/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
    323
    +0.15
    0.9%
    95
    +0.11
    0.6%
    126
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.15
    0.01
    192
    +0.11
    0.01
    306
    +0.10
    0.01
    Negative Logits
    ĨĴ
    -2.00
    °
    -1.81
    ¦
    -1.53
    Į
    -1.53
    ):
    -1.52
    valence
    -1.52
     ):
    -1.50
    ľ
    -1.47
    )):
    -1.46
    ²
    -1.39
    POSITIVE LOGITS
     licenses
    1.68
     fees
    1.55
    cribe
    1.53
     jointly
    1.53
    iosis
    1.41
     pressures
    1.41
    igate
    1.40
    soever
    1.40
     permission
    1.38
     fee
    1.33
    Activations Density 0.052%

    No Known Activations