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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 8384
    Prev
    Next
    INDEX
    Explanations

    terms related to the perpetuation or sustaining of ideas, beliefs, or conditions

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of perpetuation or continuation of actions, beliefs, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chalk
    -0.84
     aperture
    -0.69
     swollen
    -0.66
     Skydragon
    -0.66
     surg
    -0.65
     chips
    -0.65
     temperament
    -0.61
     moss
    -0.61
    ellow
    -0.60
    asso
    -0.60
    POSITIVE LOGITS
    Demand
    0.93
    advertising
    0.91
    ãĥķãĤ¡
    0.81
    OPLE
    0.78
     havoc
    0.76
    False
    0.75
    Spons
    0.73
    SPONSORED
    0.72
    Interstitial
    0.70
     Akin
    0.70
    Activations Density 0.090%

    No Known Activations