© 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. 2787
    Prev
    Next
    INDEX
    Explanations

    phrases related to political entities and structures, such as party names and laws

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political parties and related governance concepts

    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
    anches
    -0.77
    ividually
    -0.73
    actionDate
    -0.72
    ounces
    -0.71
    aneously
    -0.69
    both
    -0.68
    folios
    -0.68
    successfully
    -0.67
    listed
    -0.67
    aways
    -0.67
    POSITIVE LOGITS
     fallacy
    1.21
     motto
    1.15
     trope
    1.10
     proverb
    1.06
     playbook
    1.05
     dilemma
    1.04
     analogy
    1.03
     bullshit
    1.02
     mentality
    1.02
     thing
    0.99
    Activations Density 0.642%

    No Known Activations