© 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. 13754
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing obligations or requirements

    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
    +0.20
    1.2%
    36
    +0.13
    0.8%
    341
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.20
    0.02
    290
    +0.13
    0.01
    295
    +0.12
    0.01
    Negative Logits
    ments
    -1.92
     etc
    -1.86
    ment
    -1.72
    ning
    -1.51
    mente
    -1.41
    ging
    -1.38
     calls
    -1.34
    cens
    -1.33
    izer
    -1.29
     ruined
    -1.28
    POSITIVE LOGITS
    ħ
    2.04
    ģ
    1.78
    aked
    1.74
    ĩ
    1.73
    ¤
    1.68
    Ģ
    1.67
    ĺ
    1.64
    į
    1.63
    ī
    1.62
    ı
    1.60
    Activations Density 0.040%

    No Known Activations