© 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. 27937
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "non-" in various 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/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
    375
    +0.13
    0.8%
    130
    +0.13
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.13
    0.03
    415
    +0.13
    0.02
    172
    +0.11
    0.03
    Negative Logits
    Ķ
    -1.98
    ŀ
    -1.81
    ľĵ
    -1.79
    EventArgs
    -1.69
     CONDITIONS
    -1.65
    ======
    -1.63
    ®
    -1.57
    ever
    -1.56
    )](
    -1.52
    ¿½
    -1.52
    POSITIVE LOGITS
    -
    1.66
    ke
    1.66
    folk
    1.60
    uke
    1.58
    –
    1.51
    kes
    1.49
    quer
    1.49
    ag
    1.47
    que
    1.47
    face
    1.44
    Activations Density 0.066%

    No Known Activations