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. 3225
    Prev
    Next
    INDEX
    Explanations

    academic-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to academic achievement and scholarship

    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
     Toro
    -0.74
    aks
    -0.71
     Wanted
    -0.70
    plates
    -0.69
     Chains
    -0.68
    illon
    -0.68
    uers
    -0.67
    sin
    -0.64
    vr
    -0.64
    venge
    -0.63
    POSITIVE LOGITS
     academic
    3.50
     academics
    2.58
     Academic
    2.53
     academ
    2.42
    ademic
    2.31
     academia
    2.23
     scholarly
    2.14
     intellectual
    1.72
     educational
    1.69
     universities
    1.69
    Activations Density 0.014%

    No Known Activations