© 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. 23378
    Prev
    Next
    INDEX
    Explanations

    words related to the field of education

    oai_token-act-pair · gpt-3.5-turbo

    references to the Department of Education

    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
    olulu
    -0.71
    76561
    -0.71
     shore
    -0.66
    atos
    -0.65
    adian
    -0.63
    ãĥİ
    -0.61
    erial
    -0.59
     bis
    -0.59
     Barker
    -0.59
    aunder
    -0.58
    POSITIVE LOGITS
     Education
    1.07
    Education
    1.03
     Educ
    1.02
     Students
    0.89
    Educ
    0.89
     Programs
    0.88
     Profession
    0.84
    education
    0.84
     Practices
    0.84
     Advice
    0.83
    Activations Density 0.007%

    No Known Activations