© 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. 1-RES-SM
    11. 26203
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the name "Jung" and its variations in different contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    144
    +0.14
    0.8%
    352
    +0.11
    0.6%
    397
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.14
    0.02
    352
    +0.11
    0.02
    496
    +0.10
    0.01
    Negative Logits
    xit
    -1.81
    >&
    -1.67
    >\
    -1.55
     prejudiced
    -1.55
     nicer
    -1.54
    >/
    -1.51
    usterity
    -1.49
     gonna
    -1.48
    ck
    -1.45
     follow
    -1.45
    POSITIVE LOGITS
    ual
    1.75
    sb
    1.71
    lasses
    1.68
    itals
    1.65
    ji
    1.63
    bank
    1.61
     Fu
    1.59
    enden
    1.57
    ruptcy
    1.55
    ivals
    1.55
    Activations Density 0.097%

    No Known Activations