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. 19059
    Prev
    Next
    INDEX
    Explanations

    names of individuals and locations related to a Middle Eastern or Arabic context

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and titles of individuals associated with a particular context or event

    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
     Wilmington
    -0.77
     pregn
    -0.77
    LCS
    -0.74
    crew
    -0.73
     Titanic
    -0.71
    Irish
    -0.70
    erest
    -0.69
     cryst
    -0.69
    Seattle
    -0.68
     ster
    -0.67
    POSITIVE LOGITS
    zai
    1.39
    ullah
    1.38
    uddin
    1.37
     Hussein
    1.36
     Sheikh
    1.35
     Abbas
    1.33
     Ali
    1.33
     Abdul
    1.33
     Abu
    1.32
     Hussain
    1.32
    Activations Density 0.194%

    No Known Activations