© 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. 13572
    Prev
    Next
    INDEX
    Explanations

    terms related to legal regulations and legislation

    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
    156
    +0.20
    1.1%
    2
    +0.14
    0.8%
    186
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.20
    0.03
    181
    +0.14
    0.03
    19
    +0.13
    0.03
    Negative Logits
    ../../
    -1.52
    ighs
    -1.51
    acute
    -1.51
     Month
    -1.49
     brightness
    -1.48
     brightest
    -1.47
     fallen
    -1.46
     awake
    -1.46
    awk
    -1.43
    ĨĴ
    -1.39
    POSITIVE LOGITS
    ised
    2.15
    istic
    2.15
    istically
    2.10
    ising
    2.04
    isation
    2.00
    izing
    1.98
    ization
    1.95
    ists
    1.95
    dehyde
    1.93
    ities
    1.88
    Activations Density 0.168%

    No Known Activations