© 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. 2-RES-JB
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    references to political stances, particularly related to anti-government, anti-choice, and anti-corruption positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anti-choice and anti-government sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.88
    éĹĺ
    -0.78
    é¾įå
    -0.73
    ahime
    -0.71
    çīĪ
    -0.71
    --------------------------------------------------------
    -0.71
    å·
    -0.71
    æ©Ł
    -0.70
     ILCS
    -0.69
     adolesc
    -0.67
    POSITIVE LOGITS
    establishment
    0.86
     coalition
    0.76
    immigrant
    0.73
    fascist
    0.72
    acist
    0.71
    violence
    0.70
     suprem
    0.69
     separatists
    0.68
     repr
    0.68
    icist
    0.67
    Activations Density 0.135%

    No Known Activations