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. 11-RES-JB
    6. 8125
    Prev
    Next
    INDEX
    Explanations

    information related to displaced people, particularly in the context of refugee camps and conflict zones

    oai_token-act-pair · gpt-3.5-turbo

    references to the Rohingya refugee crisis and the conditions 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
    ãĤ¦ãĤ¹
    -0.91
    omial
    -0.76
    othy
    -0.74
    apixel
    -0.69
     Laser
    -0.69
     Brands
    -0.69
    ellig
    -0.68
     Brass
    -0.67
    esson
    -0.67
     Brilliant
    -0.65
    POSITIVE LOGITS
     fleeing
    1.67
     stranded
    1.64
     trapped
    1.42
     displaced
    1.39
     evacuated
    1.35
     escaping
    1.30
     fled
    1.27
     detained
    1.17
     flee
    1.15
     starving
    1.15
    Activations Density 0.283%

    No Known Activations