© 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. 18560
    Prev
    Next
    INDEX
    Explanations

    mentions of the Obama administration

    oai_token-act-pair · gpt-3.5-turbo

    references to the Obama administration

    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
    NetMessage
    -0.90
    requires
    -0.73
    duty
    -0.71
    agree
    -0.67
     Takeru
    -0.66
     expel
    -0.66
    perse
    -0.66
    oxide
    -0.65
    asma
    -0.65
     Ranked
    -0.65
    POSITIVE LOGITS
     administration
    1.33
     Administration
    1.15
     presidency
    1.05
     era
    1.04
     campaign
    1.03
     playbook
    1.00
     agenda
    0.99
     administrations
    0.99
     dynasty
    0.92
     regime
    0.88
    Activations Density 0.097%

    No Known Activations