© 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. 4-RES-SM
    11. 9845
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and their associated values

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.18
    1.1%
    271
    +0.15
    0.9%
    78
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.18
    0.00
    27
    +0.15
    0.04
    255
    +0.14
    -0.00
    Negative Logits
     "...
    -1.47
     medicine
    -1.35
    onomy
    -1.34
    :$$\
    -1.32
    petition
    -1.30
     (+)
    -1.27
     laundry
    -1.25
     goodbye
    -1.24
    mium
    -1.24
     medicines
    -1.22
    POSITIVE LOGITS
    ĭ
    2.15
    ĨĴ
    2.06
    Ģ
    2.04
    Ĭ
    1.96
    ı
    1.93
    Ĵ
    1.80
    Ī
    1.79
    scale
    1.79
    į
    1.79
    İ
    1.76
    Activations Density 0.180%

    No Known Activations