© 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. 32069
    Prev
    Next
    INDEX
    Explanations

    HTML tags and meta information

    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
    275
    +0.14
    0.8%
    369
    +0.12
    0.7%
    436
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.14
    0.02
    27
    +0.12
    0.02
    18
    +0.12
    0.02
    Negative Logits
    antly
    -1.77
    lication
    -1.55
    ously
    -1.50
    ogether
    -1.50
    uously
    -1.49
    inally
    -1.48
    fully
    -1.48
    initis
    -1.47
    ipes
    -1.45
    gle
    -1.44
    POSITIVE LOGITS
    ĭ
    2.64
    ·
    2.52
    ģ
    2.39
    »
    2.37
    ĸ
    2.36
    ŀ
    2.27
    ¸
    2.25
    ł
    2.20
    ¾
    2.16
    Ŀ
    2.15
    Activations Density 0.077%

    No Known Activations