© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 13605
    Prev
    Next
    INDEX
    Explanations

    topics related to legal and victim's rights issues

    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
    186
    +0.20
    1.2%
    263
    +0.15
    0.9%
    230
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.20
    0.05
    399
    +0.15
    0.04
    207
    +0.13
    0.06
    Negative Logits
     map
    -1.50
    ème
    -1.49
    rid
    -1.44
    linking
    -1.39
    Dictionary
    -1.39
    imetric
    -1.38
    ench
    -1.37
     dataset
    -1.37
     spanning
    -1.33
    PDF
    -1.32
    POSITIVE LOGITS
    ĻĤ
    3.44
    ľĵ
    2.93
    Īĺ
    2.86
    ı
    2.84
    ¿½
    2.62
    ŀ
    2.61
    ©
    2.61
    IJ
    2.53
    £
    2.53
    İ
    2.51
    Activations Density 4.625%

    No Known Activations