© 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. 8-RES-JB
    11. 6498
    Prev
    Next
    INDEX
    Explanations

    actions or situations related to consequences or rules like failing to comply or act

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compliance and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icon
    -0.69
    çīĪ
    -0.67
    okingly
    -0.65
    loo
    -0.65
    rather
    -0.64
    ateur
    -0.64
    ornia
    -0.64
     NEVER
    -0.61
    inelli
    -0.60
    Discussion
    -0.60
    POSITIVE LOGITS
     anymore
    1.21
     altogether
    0.91
     adequately
    0.87
     whatsoever
    0.79
     nor
    0.78
     properly
    0.75
     adequate
    0.71
     due
    0.70
     enough
    0.68
     sufficiently
    0.66
    Activations Density 0.386%

    No Known Activations