© 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. 0-RES-JB
    11. 6757
    Prev
    Next
    INDEX
    Explanations

    phrases related to support, encouragement, or guidance

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles ending in 'oring'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kin
    -0.59
     Species
    -0.59
     bail
    -0.59
     transmit
    -0.57
     Bid
    -0.56
     Bub
    -0.55
     spe
    -0.55
     Li
    -0.55
     indemn
    -0.55
     Roses
    -0.54
    POSITIVE LOGITS
    oring
    4.25
    ored
    3.00
    orer
    2.15
    ORED
    2.12
    ores
    2.07
    orers
    2.04
    ouring
    1.98
    orship
    1.94
    orable
    1.82
    oration
    1.75
    Activations Density 0.008%

    No Known Activations