© 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. 20480
    Prev
    Next
    INDEX
    Explanations

    words related to political ideologies, particularly focusing on Republicanism

    oai_token-act-pair · gpt-3.5-turbo

    references to political ideologies and their variations

    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
     Pwr
    -0.81
    Luck
    -0.74
    Delivery
    -0.73
    luck
    -0.72
     Completed
    -0.72
    pleted
    -0.70
     Delivery
    -0.69
    operator
    -0.68
    amsung
    -0.68
    ©¶æ¥µ
    -0.67
    POSITIVE LOGITS
     ideologically
    1.37
     ideological
    1.36
     conservatism
    1.34
     liberalism
    1.34
     adherents
    1.31
     liberals
    1.28
     neocons
    1.27
     libertarian
    1.25
     libertarians
    1.23
     leftists
    1.23
    Activations Density 1.152%

    No Known Activations