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. 16002
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and regulations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "al"

    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
     dynamically
    -0.65
     Weeks
    -0.64
     democratically
    -0.62
     sensitive
    -0.62
     Synd
    -0.60
     Presbyterian
    -0.60
     centrally
    -0.59
     Construct
    -0.59
     completely
    -0.58
     CLR
    -0.58
    POSITIVE LOGITS
    manac
    1.42
    chemy
    1.35
    chemist
    1.28
    imony
    1.28
    pine
    1.27
    leys
    1.27
    oof
    1.27
    ittle
    1.22
    imentary
    1.20
    umn
    1.19
    Activations Density 0.026%

    No Known Activations