© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11128
    Prev
    Next
    INDEX
    Explanations

    terms related to viral infections, particularly focusing on the presence and effects of HIV and hepatitis B

    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
    156
    +0.16
    0.9%
    162
    +0.15
    0.9%
    430
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.16
    0.05
    304
    +0.15
    0.04
    29
    +0.12
    0.01
    Negative Logits
     appropri
    -1.49
     mechanic
    -1.41
     reinforced
    -1.41
     rewritten
    -1.38
     compass
    -1.38
     GENERATED
    -1.38
     sanit
    -1.37
     renov
    -1.36
     grading
    -1.35
     projector
    -1.35
    POSITIVE LOGITS
    ĻĤ
    2.65
    »¿
    2.41
    ¼
    2.31
    ¢
    2.12
    ³
    2.07
    ľĵ
    2.06
    à«ĩ
    2.02
     individuals
    1.99
    ¾
    1.98
     populations
    1.98
    Activations Density 0.440%

    No Known Activations