© 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 EvalsExportsinterp-engineNEWAPI 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. 9655
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various forms and 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/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
    78
    +0.12
    0.7%
    306
    +0.11
    0.6%
    260
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.04
    53
    +0.11
    0.04
    143
    +0.11
    0.02
    Negative Logits
    ¿½
    -3.34
    Ľ
    -3.32
    Ī
    -3.27
    ¡
    -3.27
    Į
    -3.24
    Ħ
    -3.20
    ®
    -3.12
    Ĭ
    -3.08
    Ļ
    -3.06
    ĸ
    -3.05
    POSITIVE LOGITS
     accessed
    2.25
     traced
    2.21
     seen
    2.17
     easily
    2.12
     avoided
    2.12
     construed
    2.10
     remotely
    2.04
     viewed
    2.02
     categorized
    2.00
     safely
    2.00
    Activations Density 0.203%

    No Known Activations