Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 472
    Prev
    Next
    INDEX
    Explanations

    terms related to academia and education, particularly focused on subjects such as mathematics, science, and literature, as well as academic titles and research fields

    oai_token-act-pair · gpt-3.5-turbo

    references to educational subjects and skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.86
    ãĥ¼ãĥ³
    -0.85
    onda
    -0.82
    bucks
    -0.80
    boss
    -0.76
    spawn
    -0.73
    engers
    -0.72
     impunity
    -0.71
    enting
    -0.71
    earances
    -0.71
    POSITIVE LOGITS
     maths
    1.27
     mathematics
    1.25
     sciences
    1.22
     humanities
    1.19
     mathematic
    1.12
     neuroscience
    1.12
     astronomy
    1.09
     algebra
    1.07
     anthropology
    1.06
     sociology
    1.03
    Activations Density 0.306%

    No Known Activations