© 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. 18635
    Prev
    Next
    INDEX
    Explanations

    information related to university activities, reputation management, and community response to events

    oai_token-act-pair · gpt-3.5-turbo

    references to university policies and student conduct

    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
     Pwr
    -0.79
    etheless
    -0.74
    oshenko
    -0.72
    igree
    -0.71
     piston
    -0.70
    ustom
    -0.70
    emet
    -0.68
    zbollah
    -0.68
    eware
    -0.67
     fisherman
    -0.67
    POSITIVE LOGITS
     campus
    2.25
     faculty
    2.15
    campus
    2.04
     university
    2.03
     campuses
    2.02
     Campus
    2.02
     Faculty
    2.01
    Students
    1.94
     Student
    1.93
     professors
    1.93
    Activations Density 1.122%

    No Known Activations