© 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. 31493
    Prev
    Next
    INDEX
    Explanations

    punctuation and various types of sentence endings

    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
    258
    +0.14
    0.8%
    23
    +0.14
    0.8%
    189
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.14
    0.08
    258
    +0.14
    0.08
    138
    +0.12
    0.07
    Negative Logits
    adren
    -1.66
     thereof
    -1.63
    /$
    -1.59
    adin
    -1.59
    -$
    -1.57
     frequ
    -1.51
    fielder
    -1.49
    :%
    -1.46
    castle
    -1.44
    .%
    -1.43
    POSITIVE LOGITS
    ¦
    2.06
    ³
    2.05
    Į
    2.01
    İ
    1.95
    į
    1.94
     Then
    1.94
    Ī
    1.91
    ĥ
    1.87
    §
    1.76
    ī
    1.74
    Activations Density 0.350%

    No Known Activations