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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 4716
    Prev
    Next
    INDEX
    Explanations

    mentions of specific ages in combination with school levels, such as "freshman" or "sophomore."

    oai_token-act-pair · gpt-3.5-turbo

    details about students' educational backgrounds and classifications

    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
    ablishment
    -0.79
    ür
    -0.72
    ichick
    -0.68
     organisations
    -0.68
    pmwiki
    -0.67
     monopoly
    -0.67
    orthy
    -0.67
    ãĥķãĤ¡
    -0.66
    osponsors
    -0.65
    anyahu
    -0.64
    POSITIVE LOGITS
     freshman
    1.73
     sophomore
    1.70
     freshmen
    1.62
     classmate
    1.61
     student
    1.49
     classmates
    1.39
     junior
    1.36
     graduating
    1.33
    arsity
    1.28
    omore
    1.26
    Activations Density 0.398%

    No Known Activations