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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 6777
    Prev
    Next
    INDEX
    Explanations

    academic titles and affiliations of university professors

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts, particularly in relation to academic institutions and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adesh
    -0.77
    女
    -0.72
     inval
    -0.71
    pour
    -0.71
    rats
    -0.70
    verage
    -0.69
    LOAD
    -0.68
    artifacts
    -0.67
    SPONSORED
    -0.66
    luck
    -0.66
    POSITIVE LOGITS
     University
    1.64
     Institute
    1.42
    University
    1.26
     Smithsonian
    1.24
     Carnegie
    1.22
     Brookings
    1.20
     Faculty
    1.19
     Harvard
    1.18
     Yale
    1.18
     NYU
    1.18
    Activations Density 0.085%

    No Known Activations