© 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. 11-RES-JB
    11. 24563
    Prev
    Next
    INDEX
    Explanations

    announcements or declarations of plans, support, resignations, or actions made by individuals in various positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to announcements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLIED
    -0.70
    imeo
    -0.70
    enium
    -0.67
    angs
    -0.67
    otin
    -0.65
    pmwiki
    -0.64
    osate
    -0.63
    rendered
    -0.63
    erers
    -0.62
    ãĥĥãĥī
    -0.62
    POSITIVE LOGITS
     plans
    1.32
     Plans
    0.93
     partnerships
    0.88
     layoffs
    0.87
     that
    0.84
     intentions
    0.82
     arrangements
    0.79
     intention
    0.77
     goodbye
    0.75
     impending
    0.75
    Activations Density 0.067%

    No Known Activations