© 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. 31796
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to machine learning and optimization frameworks

    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
    240
    +0.16
    0.9%
    204
    +0.14
    0.8%
    400
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.16
    0.10
    35
    +0.14
    0.01
    240
    +0.14
    -0.01
    Negative Logits
    ]>
    -1.75
     warranty
    -1.59
    posted
    -1.58
     dissolved
    -1.56
    ADVERTISEMENT
    -1.56
     ">
    -1.55
    photos
    -1.53
     clearance
    -1.52
     reinst
    -1.50
     Photos
    -1.50
    POSITIVE LOGITS
     algorithms
    2.51
     algorithm
    2.50
    oretic
    2.15
     Bayesian
    2.13
     computational
    2.12
     computes
    2.12
     dataset
    2.11
     embeddings
    2.04
     probabil
    2.04
     Gaussian
    2.01
    Activations Density 1.742%

    No Known Activations