© 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. 6099
    Prev
    Next
    INDEX
    Explanations

    instances where actions are being taken or enabled by specific measures or techniques

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to encouragement and support

    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
     Revival
    -0.67
     Ake
    -0.65
    erence
    -0.65
     disappointment
    -0.63
     Saunders
    -0.62
     Lies
    -0.58
    Winged
    -0.58
     Harding
    -0.58
     Heisman
    -0.57
     irony
    -0.57
    POSITIVE LOGITS
     effectively
    1.01
     efficiently
    0.92
     able
    0.88
     automatically
    0.87
    forth
    0.86
     ensured
    0.83
     streng
    0.77
     empowered
    0.76
     confidently
    0.76
     gradually
    0.75
    Activations Density 0.490%

    No Known Activations