© 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. 28175
    Prev
    Next
    INDEX
    Explanations

    structured formatting related to coding and documentation

    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
    419
    +0.13
    0.7%
    198
    +0.13
    0.7%
    367
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.13
    0.14
    129
    +0.13
    0.01
    478
    +0.11
    -0.01
    Negative Logits
    °
    -1.95
    ļ
    -1.79
    ®
    -1.78
    º
    -1.73
    ij
    -1.72
    Ŀ
    -1.71
    µ
    -1.70
    ¿
    -1.67
    ĭ
    -1.65
    ¾
    -1.65
    POSITIVE LOGITS
    ectomy
    1.49
    optera
    1.43
    oscopy
    1.41
    :**
    1.39
    rogenic
    1.37
     DES
    1.36
    idden
    1.34
    smallcaps
    1.32
    :`
    1.29
    leftarrow
    1.29
    Activations Density 3.824%

    No Known Activations