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. 10-RES-JB
    6. 9498
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific types of professions or fields of expertise

    oai_token-act-pair · gpt-3.5-turbo

    characters or elements within the entertainment and cultural sectors

    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
     afterward
    -0.73
     nonetheless
    -0.64
    idav
    -0.61
    starter
    -0.61
    ebin
    -0.60
     accordingly
    -0.60
     solicitation
    -0.59
     McH
    -0.59
    ullivan
    -0.59
     sooner
    -0.58
    POSITIVE LOGITS
     civilisation
    1.08
     British
    0.81
     European
    0.79
    British
    0.78
     global
    0.77
     world
    0.73
     Anglo
    0.72
     Indonesian
    0.72
    ieval
    0.72
     mankind
    0.71
    Activations Density 0.844%

    No Known Activations