© 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. 9261
    Prev
    Next
    INDEX
    Explanations

    phrases expressing desires or preferences

    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
    478
    +0.17
    0.9%
    226
    +0.13
    0.7%
    89
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    226
    +0.17
    0.05
    52
    +0.13
    0.05
    420
    +0.12
    0.04
    Negative Logits
    ľĵ
    -2.34
    ł
    -2.17
    Ĺ
    -2.17
    »¿
    -2.16
    Ļª
    -2.13
    ľ
    -2.06
    İ
    -2.03
    ļ
    -2.02
    ı
    -2.02
    ¢
    -2.01
    POSITIVE LOGITS
     recommend
    2.88
     prefer
    2.45
     hope
    2.41
     like
    2.34
     advise
    2.14
     appreciate
    2.10
    nt
    2.10
     love
    2.09
     suggest
    2.03
     consider
    1.97
    Activations Density 0.121%

    No Known Activations