© 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. 15150
    Prev
    Next
    INDEX
    Explanations

    sentences related to work and time management

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to startup culture and innovation

    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
     spitting
    -0.77
     cone
    -0.76
     censored
    -0.74
     sacked
    -0.73
     covenant
    -0.73
     tube
    -0.72
     bloc
    -0.72
     hatch
    -0.72
     wire
    -0.72
     aven
    -0.71
    POSITIVE LOGITS
    Consider
    1.55
    Fortunately
    1.51
    However
    1.45
    According
    1.43
    Recently
    1.42
    Nevertheless
    1.42
    Advertisement
    1.41
    Recent
    1.40
    Specifically
    1.40
    Unfortunately
    1.40
    Activations Density 0.465%

    No Known Activations