© 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. 7-RES-JB
    11. 16756
    Prev
    Next
    INDEX
    Explanations

    technical or professional terms related to various industries

    oai_token-act-pair · gpt-3.5-turbo

    references to businesses and industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anyway
    -0.79
     Iranians
    -0.77
    —"
    -0.75
     aides
    -0.72
    apo
    -0.72
     afterward
    -0.70
     deport
    -0.68
     judgments
    -0.68
     Kissinger
    -0.68
    achment
    -0.67
    POSITIVE LOGITS
     renowned
    0.92
     legendary
    0.84
     renown
    0.83
     acclaimed
    0.83
     innovative
    0.82
     Kickstarter
    0.81
    ĸļ
    0.78
     collaborative
    0.77
     amazing
    0.77
     themed
    0.77
    Activations Density 1.198%

    No Known Activations