© 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. 10-RES-JB
    11. 23409
    Prev
    Next
    INDEX
    Explanations

    terms related to social, political, and historical issues or injustices

    oai_token-act-pair · gpt-3.5-turbo

    keywords and concepts related to social justice and inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneously
    -0.70
    olicited
    -0.65
    renheit
    -0.65
    \\\\\\\\
    -0.62
    rition
    -0.62
    batch
    -0.62
    -+-+
    -0.61
    riel
    -0.61
    LAND
    -0.60
    olia
    -0.60
    POSITIVE LOGITS
     aspect
    1.22
     component
    1.04
     portion
    0.99
     continuum
    0.98
     gap
    0.97
     paradigm
    0.96
     element
    0.95
     equation
    0.94
     bandwagon
    0.94
     lobby
    0.94
    Activations Density 0.444%

    No Known Activations