© 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. 1-RES-SM
    11. 24887
    Prev
    Next
    INDEX
    Explanations

    chemical compounds, specifically those containing benzene or related structures

    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
    43
    +0.17
    1.0%
    111
    +0.11
    0.6%
    321
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.17
    0.02
    410
    +0.11
    0.01
    94
    +0.11
    0.01
    Negative Logits
    VIS
    -1.56
    ITH
    -1.54
     certain
    -1.50
    cludes
    -1.44
    irc
    -1.43
     tuning
    -1.42
    '));
    -1.40
     ///<
    -1.40
    MER
    -1.39
    ÑģÑĤÑĮ
    -1.39
    POSITIVE LOGITS
    ¾
    1.91
    ĸ
    1.90
    º
    1.90
    ī
    1.86
    acks
    1.85
    owitz
    1.84
    İ
    1.83
    ĥ
    1.81
    §
    1.80
    oyl
    1.80
    Activations Density 0.061%

    No Known Activations