Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3896
    Prev
    Next
    INDEX
    Explanations

    negative situations or obstacles

    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
    è¦ļéĨĴ
    -0.83
     Mandatory
    -0.77
     Historically
    -0.76
    ©¶æ
    -0.71
     bloc
    -0.71
    stakes
    -0.69
    artisan
    -0.68
    ãĥ¼ãĤ¯
    -0.66
    incial
    -0.66
    FactoryReloaded
    -0.65
    POSITIVE LOGITS
     bothering
    1.07
     anymore
    0.97
     bud
    0.95
    hin
    0.94
     bother
    0.92
     anybody
    0.89
     noticing
    0.87
     blinking
    0.87
     bothered
    0.87
     reply
    0.87
    Activations Density 0.399%

    No Known Activations