© 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. 10075
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or bans

    oai_token-act-pair · gpt-3.5-turbo

    themes related to change and its impact on society

    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
    SPONSORED
    -0.85
    bia
    -0.75
    Rail
    -0.71
    ç«
    -0.68
    iscons
    -0.64
    aye
    -0.63
     Rah
    -0.63
    ificantly
    -0.62
    antically
    -0.62
     wal
    -0.62
    POSITIVE LOGITS
     dictators
    0.87
     endings
    0.78
     fools
    0.75
     shortcuts
    0.74
     weddings
    0.74
     nowadays
    0.73
     storytelling
    0.71
     ALWAYS
    0.70
     Journalism
    0.70
     ¯
    0.70
    Activations Density 1.427%

    No Known Activations