© 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 EvalsExportsAPI 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. 10254
    Prev
    Next
    INDEX
    Explanations

    function definitions and method parameters

    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
    +0.16
    0.9%
    186
    +0.16
    0.9%
    153
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.16
    -0.02
    187
    +0.16
    0.07
    210
    +0.14
    0.03
    Negative Logits
    oplan
    -1.75
    NON
    -1.74
     LLP
    -1.47
    lining
    -1.45
     framework
    -1.44
    clamation
    -1.44
    DOCTYPE
    -1.42
     ont
    -1.41
    Acknowledgments
    -1.40
    **:
    -1.39
    POSITIVE LOGITS
    Ķ
    3.02
    ľĵ
    2.97
    §
    2.88
    Ĺ
    2.81
    «
    2.79
    Ĥ
    2.79
    ģ
    2.69
    ľ
    2.69
    Īĺ
    2.66
    ĻĤ
    2.64
    Activations Density 3.491%

    No Known Activations