© 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. 15628
    Prev
    Next
    INDEX
    Explanations

    informational content

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal experiences and time spent

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
     Mankind
    -0.53
    enery
    -0.51
    iage
    -0.51
    thood
    -0.51
    Built
    -0.50
    é£
    -0.49
     Canaveral
    -0.49
     phys
    -0.48
    ãĥ¥
    -0.47
    POSITIVE LOGITS
    endix
    0.62
    ascript
    0.62
     reader
    0.62
     summar
    0.62
     summarize
    0.61
     partisan
    0.59
     rhetorical
    0.57
     Editorial
    0.57
     analytic
    0.57
     summarizes
    0.56
    Activations Density 2.830%

    No Known Activations