© 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. 10-RES-JB
    11. 20485
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms related to business, contracts, and technology

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and specific terms related to measurements or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRE
    -0.81
    Large
    -0.80
    Natural
    -0.80
    Hor
    -0.78
    Rust
    -0.77
    Recent
    -0.76
    Dust
    -0.76
    Weather
    -0.75
    Built
    -0.75
    ccoli
    -0.75
    POSITIVE LOGITS
     status
    0.99
     approach
    0.90
     scheme
    0.90
     system
    0.87
     protocol
    0.87
     zone
    0.85
     slate
    0.85
     designation
    0.85
     capability
    0.85
     phenomenon
    0.85
    Activations Density 0.244%

    No Known Activations