© 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. 1-RES-JB
    11. 784
    Prev
    Next
    INDEX
    Explanations

    technical terms related to astrophysics

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Ast" and related contextual terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cific
    -0.88
    ä¹ĭ
    -0.74
    cules
    -0.73
    çīĪ
    -0.70
    flix
    -0.67
    submit
    -0.64
    sburgh
    -0.63
    invoke
    -0.63
    cation
    -0.63
    ted
    -0.63
    POSITIVE LOGITS
    rament
    1.00
     Ast
    0.96
    roph
    0.94
    Ast
    0.87
    igmat
    0.84
    acio
    0.82
    uria
    0.79
    rolog
    0.77
    oga
    0.76
    rology
    0.75
    Activations Density 0.005%

    No Known Activations