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. 8029
    Prev
    Next
    INDEX
    Explanations

    medical terms related to different body parts, such as "hockey sticks", "brains", and "ACL"

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific concepts or phenomena

    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
     nutshell
    -0.64
     TODAY
    -0.62
    yssey
    -0.61
     midday
    -0.59
     awaits
    -0.59
     380
    -0.58
    !'"
    -0.57
     Goodbye
    -0.57
    utenberg
    -0.56
     astonished
    -0.56
    POSITIVE LOGITS
    âĢ
    1.12
     âĢ
    1.01
    âĶ
    0.85
    Ì
    0.85
    / 
    0.83
    âķ
    0.83
    Í
    0.81
    âī
    0.81
    âĨ
    0.79
    âĸ
    0.78
    Activations Density 1.132%

    No Known Activations