© 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. 15680
    Prev
    Next
    INDEX
    Explanations

    instances where an action or event leads to a specific outcome or result

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a" and its related contexts

    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
    forge
    -0.79
    itiveness
    -0.77
    pages
    -0.73
    \)
    -0.66
    views
    -0.65
    conom
    -0.64
    sama
    -0.62
    files
    -0.62
    \.
    -0.60
    arts
    -0.59
    POSITIVE LOGITS
     result
    1.57
     precaution
    1.35
     consequence
    1.26
     workaround
    0.98
     gesture
    0.94
     consolation
    0.94
     tribute
    0.94
     reward
    0.94
     punishment
    0.92
     reminder
    0.91
    Activations Density 0.098%

    No Known Activations