© 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. 6563
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal identity and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal experiences and perspectives related to social issues

    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
    catentry
    -0.87
    ELS
    -0.71
     enthusi
    -0.71
    MpServer
    -0.71
    Bridge
    -0.67
    mins
    -0.66
    EDIT
    -0.66
    DCS
    -0.63
    updated
    -0.62
     Scenes
    -0.62
    POSITIVE LOGITS
     paycheck
    0.84
     yourself
    0.81
     offend
    0.80
     obey
    0.79
     citizenship
    0.78
     ain
    0.73
     oneself
    0.73
     transgress
    0.71
     yourselves
    0.71
     obe
    0.70
    Activations Density 0.655%

    No Known Activations