© 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. 7-RES-JB
    11. 17124
    Prev
    Next
    INDEX
    Explanations

    words related to actions being taken to address various issues, such as combatting terrorism, climate change, and other global challenges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fighting or addressing various societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    felt
    -0.78
     liner
    -0.70
    ships
    -0.68
    ittal
    -0.67
     announ
    -0.67
    DragonMagazine
    -0.67
     rubbed
    -0.62
    ubes
    -0.62
    Reviewer
    -0.60
    Used
    -0.60
    POSITIVE LOGITS
     trafficking
    0.86
     terrorism
    0.85
     obesity
    0.78
     Zika
    0.77
     piracy
    0.74
     harassment
    0.73
     runaway
    0.72
     combating
    0.72
     poverty
    0.72
     homelessness
    0.72
    Activations Density 0.181%

    No Known Activations