© 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. 2717
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and ethical matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and ethical issues, particularly in the context of rights and regulations

    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
    imus
    -0.77
    lihood
    -0.75
    ularity
    -0.74
     <+
    -0.71
     Happiness
    -0.69
    Minecraft
    -0.68
    ima
    -0.68
    itude
    -0.67
    imov
    -0.65
    sg
    -0.65
    POSITIVE LOGITS
     experts
    1.27
     officials
    1.21
     bureau
    1.17
     specialist
    1.16
     expert
    1.15
     adviser
    1.14
     authorities
    1.13
     spokesman
    1.12
     consultant
    1.10
     spokeswoman
    1.09
    Activations Density 0.327%

    No Known Activations