© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20219
    Prev
    Next
    INDEX
    Explanations

    instances of the word "provision" with varying strengths of activation, where higher activation values indicate stronger matches

    oai_token-act-pair · gpt-3.5-turbo

    legal or regulatory terms related to provisions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritz
    -0.68
    Magikarp
    -0.67
    ampa
    -0.65
    CV
    -0.65
    kson
    -0.61
    Arc
    -0.61
    hiro
    -0.61
    Textures
    -0.60
     palms
    -0.59
     wander
    -0.59
    POSITIVE LOGITS
    ality
    1.04
    ally
    1.01
    witz
    0.99
    alities
    0.96
    ional
    0.85
    arians
    0.85
    arian
    0.83
    IAL
    0.81
    mental
    0.78
    aler
    0.75
    Activations Density 0.040%

    No Known Activations