© 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 EvalsExportsAPI 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. 10410
    Prev
    Next
    INDEX
    Explanations

    statistical data and results related to medical conditions and treatments

    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
    369
    +0.21
    1.2%
    199
    +0.12
    0.7%
    492
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.21
    0.06
    203
    +0.12
    0.06
    369
    +0.11
    0.03
    Negative Logits
     encryption
    -1.60
    äºİ
    -1.46
    аеÑĤ
    -1.44
    iser
    -1.44
    äºĨ
    -1.39
    availability
    -1.38
    emption
    -1.38
    çĿĢ
    -1.38
     habitat
    -1.37
    ests
    -1.35
    POSITIVE LOGITS
    ĥ½
    3.35
    ·¸
    3.35
    ¾
    3.20
    3.08
    ↵
    3.08
    3.08
    ↵
    3.08
    3.08
     ↵
    3.08
    č↵
    3.08
    Activations Density 0.231%

    No Known Activations