© 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. 9-RES-JB
    11. 4814
    Prev
    Next
    INDEX
    Explanations

    words related to political figures, such as names of politicians and their titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political figures and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hispanic
    -0.87
     honoring
    -0.86
     unauthorized
    -0.81
     utilizing
    -0.81
     videot
    -0.81
     tumors
    -0.81
     honor
    -0.80
    Arizona
    -0.80
     Grateful
    -0.80
     nonviolent
    -0.78
    POSITIVE LOGITS
     Downing
    1.13
     Fraser
    1.13
     Wales
    1.12
     Miliband
    1.11
     Scotland
    1.10
     Davies
    1.06
     Cardiff
    1.05
     Thatcher
    1.04
     Corbyn
    1.03
     Buckingham
    1.03
    Activations Density 0.397%

    No Known Activations