© 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. 9951
    Prev
    Next
    INDEX
    Explanations

    information related to cannabis and its chemical compounds

    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
    +0.22
    1.3%
    17
    +0.21
    1.2%
    231
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.22
    0.42
    4
    +0.21
    0.41
    428
    +0.13
    0.32
    Negative Logits
    idenote
    -1.84
    ************************
    -1.61
    sequently
    -1.55
    atement
    -1.51
    MSO
    -1.47
     conclusion
    -1.44
    =======================
    -1.43
    ****************************************************************************
    -1.42
     ensued
    -1.41
    ********************************
    -1.40
    POSITIVE LOGITS
    ¼
    1.64
     âĢ¦
    1.53
    ?",
    1.50
    ĭ
    1.42
    ¿
    1.39
    ¹
    1.38
     microM
    1.37
    /
    1.35
     (),
    1.34
    §
    1.32
    Activations Density 3.501%

    No Known Activations