© 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. 27824
    Prev
    Next
    INDEX
    Explanations

    references to court cases and legal proceedings

    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
    271
    +0.19
    1.1%
    410
    +0.15
    0.9%
    287
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.19
    0.07
    271
    +0.15
    0.01
    202
    +0.14
    0.04
    Negative Logits
    olds
    -1.98
    tons
    -1.79
     same
    -1.66
    )',
    -1.62
     PST
    -1.59
     Scots
    -1.56
     NZ
    -1.54
     UK
    -1.53
     respectively
    -1.51
    its
    -1.51
    POSITIVE LOGITS
    ´
    4.94
    ĥ½
    4.74
    ¹
    4.72
    Ĩ
    4.70
    į
    4.65
    ĭ
    4.61
    ł
    4.57
    Į
    4.56
    ľ
    4.54
    ¶
    4.51
    Activations Density 0.270%

    No Known Activations