© 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. 0-RES-JB
    11. 16346
    Prev
    Next
    INDEX
    Explanations

    references to academic grading systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic performance and evaluation, particularly grades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inf
    -0.67
     Sup
    -0.66
    oggle
    -0.66
     amb
    -0.64
    ront
    -0.63
     event
    -0.62
    entity
    -0.62
     Expand
    -0.61
    LA
    -0.61
    hack
    -0.60
    POSITIVE LOGITS
     grades
    4.23
     grade
    2.10
     grading
    1.89
     graded
    1.79
     Grade
    1.65
    Grade
    1.56
    grades
    1.51
     GPA
    1.51
     rankings
    1.20
     classes
    1.19
    Activations Density 0.024%

    No Known Activations