© 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. 1-RES-JB
    11. 9390
    Prev
    Next
    INDEX
    Explanations

    mentions of students in educational contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to students in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bilateral
    -0.67
    UTERS
    -0.65
     bis
    -0.61
     Species
    -0.61
     Shore
    -0.61
     tame
    -0.60
     leash
    -0.60
     Bots
    -0.59
     magn
    -0.59
     Cape
    -0.59
    POSITIVE LOGITS
    Students
    1.26
     students
    1.15
    student
    1.09
     Students
    1.03
    uates
    0.96
    Student
    0.92
    girls
    0.91
     graduates
    0.89
    kids
    0.89
     tuition
    0.87
    Activations Density 0.026%

    No Known Activations