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. 6-RES-JB
    6. 12516
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Dallas."

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Dallas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oys
    -0.79
    iltration
    -0.76
    icably
    -0.73
     captcha
    -0.69
    unda
    -0.68
    âĵĺ
    -0.67
    ebook
    -0.66
    elvet
    -0.65
    DIV
    -0.65
     menstru
    -0.65
    POSITIVE LOGITS
     Mavericks
    1.23
     Cowboys
    1.04
    Stars
    0.96
     Stars
    0.92
     Dallas
    0.81
    Dallas
    0.81
    burg
    0.80
    iens
    0.78
    illo
    0.77
    hyde
    0.74
    Activations Density 0.020%

    No Known Activations