© 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. 2-RES-SM
    11. 31834
    Prev
    Next
    INDEX
    Explanations

    intensifiers and expressions of strong emotions or opinions

    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
    246
    +0.12
    0.7%
    482
    +0.11
    0.7%
    477
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.12
    0.04
    386
    +0.11
    0.02
    14
    +0.11
    0.04
    Negative Logits
    Ģ
    -3.61
    Ĩ
    -3.58
    ļ
    -3.42
    ¶
    -3.28
    ħ
    -3.22
    Ī
    -3.20
    Ĵ
    -3.18
    Ĥ¬
    -3.16
    Ķ
    -3.09
    ĨĴ
    -3.08
    POSITIVE LOGITS
     drag
    1.78
     luck
    1.69
     appreciate
    1.55
     piss
    1.54
     shy
    1.51
     pissed
    1.48
     hurt
    1.47
     bump
    1.39
     upset
    1.39
    review
    1.38
    Activations Density 0.141%

    No Known Activations