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. 15189
    Prev
    Next
    INDEX
    Explanations

    chemical compounds or elements

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to scientific or technical concepts

    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
     eleph
    -0.86
     pione
    -0.84
    Þ
    -0.81
     nomine
    -0.76
     exting
    -0.73
    Ý
    -0.70
     enthusi
    -0.69
    ą
    -0.69
    é¾įå¥
    -0.69
    À
    -0.69
    POSITIVE LOGITS
    idy
    0.64
    itas
    0.62
    akia
    0.61
    ENA
    0.60
    acy
    0.59
    enge
    0.58
    ICE
    0.57
    oor
    0.57
    ature
    0.57
    etry
    0.57
    Activations Density 0.266%

    No Known Activations