© 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. 9-RES-JB
    11. 2484
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms or topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rental
    -0.82
     estate
    -0.82
     wardrobe
    -0.81
     nightly
    -0.76
     truce
    -0.76
     amnesty
    -0.76
     renting
    -0.75
     bund
    -0.75
     resignation
    -0.75
     cabinet
    -0.75
    POSITIVE LOGITS
    Researchers
    1.88
    Scientists
    1.75
    Explore
    1.63
    Professor
    1.51
    Writing
    1.44
    Using
    1.43
    Abstract
    1.42
    Previous
    1.40
    Journal
    1.39
    Methods
    1.36
    Activations Density 0.235%

    No Known Activations