© 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. 28959
    Prev
    Next
    INDEX
    Explanations

    key identifiers, dates, and legal references

    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
    351
    +0.16
    0.9%
    169
    +0.13
    0.7%
    315
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.16
    0.04
    157
    +0.13
    0.06
    21
    +0.12
    0.04
    Negative Logits
     reminder
    -1.75
     examples
    -1.57
     cousins
    -1.57
     hierarch
    -1.57
     life
    -1.51
     reign
    -1.50
     sisters
    -1.49
     families
    -1.49
     magnitude
    -1.48
     wings
    -1.47
    POSITIVE LOGITS
    »¿
    3.23
    ±
    2.89
    ¹
    2.85
    ¯
    2.75
    ¶
    2.71
    ģ
    2.67
    »
    2.63
    ī
    2.60
    ½
    2.56
    Ķ
    2.54
    Activations Density 0.557%

    No Known Activations