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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17638
    Prev
    Next
    INDEX
    Explanations

    references to astronomy and space exploration

    oai_token-act-pair · gpt-3.5-turbo

    references to astronomical observation and discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    respective
    -0.81
    sic
    -0.74
     requisite
    -0.70
    erning
    -0.70
     ascertain
    -0.67
     duly
    -0.67
    arb
    -0.67
    âĢIJ
    -0.67
    enance
    -0.65
     âī¤
    -0.65
    POSITIVE LOGITS
     Scientists
    0.66
    Enlarge
    0.64
     bigger
    0.61
     Nasa
    0.60
     Lets
    0.60
     scientists
    0.59
     Edison
    0.59
     tries
    0.59
     stuff
    0.58
     says
    0.57
    Activations Density 1.605%

    No Known Activations