© 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. 6401
    Prev
    Next
    INDEX
    Explanations

    ways to prevent physical objects from breaking or slipping

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and structural integrity

    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
    åŃ
    -0.78
    cknowled
    -0.73
    MQ
    -0.72
    etus
    -0.71
    MRI
    -0.69
    LM
    -0.69
    DEM
    -0.67
    ihadi
    -0.67
    grand
    -0.67
    LIST
    -0.67
    POSITIVE LOGITS
     moisture
    1.13
     uneven
    1.06
     seams
    1.05
     coating
    1.05
     pores
    1.05
     surfaces
    1.04
     insulation
    1.01
     fibers
    1.00
     contaminants
    0.97
     brittle
    0.95
    Activations Density 0.489%

    No Known Activations