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. 0-RES-JB
    6. 8863
    Prev
    Next
    INDEX
    Explanations

    mentions of locations in an academic setting

    oai_token-act-pair · gpt-3.5-turbo

    references to a university or college campus

    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
    ι
    -0.66
    mir
    -0.63
    MH
    -0.62
     Thrust
    -0.60
    rs
    -0.59
    OIL
    -0.58
     Accessories
    -0.58
    dig
    -0.58
    tt
    -0.57
     Ago
    -0.56
    POSITIVE LOGITS
     campus
    3.76
     Campus
    2.88
     campuses
    2.86
    campus
    2.72
     university
    1.80
     faculty
    1.65
     dorm
    1.47
     semester
    1.46
     student
    1.44
    Students
    1.44
    Activations Density 0.017%

    No Known Activations