© 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. 9-RES-JB
    11. 1358
    Prev
    Next
    INDEX
    Explanations

    instructions for cutting food items

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to food preparation and cooking techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bnb
    -0.76
     Monitoring
    -0.74
     Investors
    -0.69
     Siren
    -0.67
    monitor
    -0.66
    ãģ®å®
    -0.65
    âĹ¼
    -0.65
    ãĤ¼
    -0.65
     privilege
    -0.64
    Effects
    -0.64
    POSITIVE LOGITS
     halves
    1.21
     shapes
    1.14
     pieces
    1.12
     paste
    1.06
     shape
    1.06
     cubes
    1.03
     length
    1.01
     thinner
    0.99
     diameter
    0.99
     lengths
    0.98
    Activations Density 0.215%

    No Known Activations