© 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. 1-RES-JB
    11. 24131
    Prev
    Next
    INDEX
    Explanations

    phrases related to limitations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to warnings or conditions that need to be acknowledged

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urgy
    -0.75
     Therapy
    -0.73
     Relations
    -0.72
     relations
    -0.70
     Actions
    -0.69
     Scenes
    -0.68
    ivery
    -0.67
    ships
    -0.66
     Printing
    -0.64
    NetMessage
    -0.64
    POSITIVE LOGITS
     caveats
    1.24
     caveat
    1.17
     empt
    0.99
     disclaimer
    0.98
    claimer
    0.90
     disclaim
    0.90
    ptions
    0.87
    ño
    0.85
     caution
    0.81
     guiActiveUn
    0.76
    Activations Density 0.019%

    No Known Activations