© 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. 21686
    Prev
    Next
    INDEX
    Explanations

    words related to combating or fighting against various societal issues or challenges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to combating various social and global issues

    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
    ĸļ
    -0.77
    DragonMagazine
    -0.77
    ittal
    -0.73
     Joined
    -0.69
     congratulations
    -0.68
     Zup
    -0.68
     Minutes
    -0.67
    subject
    -0.66
    ographs
    -0.64
    cade
    -0.63
    POSITIVE LOGITS
     extremism
    1.21
     corruption
    1.20
     poverty
    1.14
     piracy
    1.13
     terrorism
    1.12
     obesity
    1.09
     discrimination
    1.08
     racism
    1.08
     illiter
    1.08
     homophobia
    1.07
    Activations Density 0.197%

    No Known Activations