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. 24225
    Prev
    Next
    INDEX
    Explanations

    keywords related to the central theme or main focus of a piece of content

    oai_token-act-pair · gpt-3.5-turbo

    discussions centered around specific focal points or themes

    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
    mia
    -0.75
    corn
    -0.67
     Rebell
    -0.64
    ibrary
    -0.62
    ania
    -0.61
    OUGH
    -0.61
    uddin
    -0.60
    conduct
    -0.59
     PRESIDENT
    -0.59
    carry
    -0.59
    POSITIVE LOGITS
    rite
    0.90
     shifts
    0.81
     groups
    0.81
    ussed
    0.80
     on
    0.80
     group
    0.75
     shift
    0.74
     Groups
    0.74
    ivated
    0.74
     squarely
    0.74
    Activations Density 0.039%

    No Known Activations