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. 16003
    Prev
    Next
    INDEX
    Explanations

    references to movement across borders and related circumstances

    oai_token-act-pair · gpt-3.5-turbo

    themes related to migration and the challenges faced by displaced individuals

    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
     stopp
    -0.78
     trolling
    -0.77
     typo
    -0.76
     overest
    -0.71
     Thief
    -0.71
     bluff
    -0.71
     plagiar
    -0.70
     stunts
    -0.69
     Doomsday
    -0.68
     eyebrow
    -0.68
    POSITIVE LOGITS
     families
    1.23
     relatives
    1.22
     homes
    1.18
     adoptive
    1.18
     homeland
    1.14
     resettlement
    1.08
     ancestral
    1.05
     home
    1.05
     family
    1.02
     grandparents
    1.02
    Activations Density 0.359%

    No Known Activations