© 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. 8-RES-JB
    11. 20221
    Prev
    Next
    INDEX
    Explanations

    descriptions of advancements and technologies related to autonomous vehicles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to autonomous vehicles and robotics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tar
    -0.82
     rye
    -0.79
     cigars
    -0.76
     Sabb
    -0.75
     dues
    -0.74
    ospons
    -0.74
     Lent
    -0.72
     Tradition
    -0.72
     Estate
    -0.71
    iversary
    -0.71
    POSITIVE LOGITS
     robotic
    1.21
     robots
    1.19
     programmed
    1.18
     robot
    1.15
     sensors
    1.15
     robotics
    1.13
    onomous
    1.12
     autonomous
    1.11
     drones
    1.08
     technology
    1.08
    Activations Density 0.600%

    No Known Activations