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. 6199
    Prev
    Next
    INDEX
    Explanations

    references to dates or time intervals

    oai_token-act-pair · gpt-3.5-turbo

    references to significant individuals and events in film and politics

    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
     PLEASE
    -0.62
    maxwell
    -0.61
     âĵĺ
    -0.59
    ,,,,
    -0.58
    morrow
    -0.57
    anty
    -0.56
    oooooooooooooooo
    -0.56
     CONTIN
    -0.55
    hend
    -0.54
    eric
    -0.54
    POSITIVE LOGITS
     previous
    0.99
     earlier
    0.95
     predecessor
    0.94
     predecessors
    0.90
     preceding
    0.81
     inception
    0.80
     prior
    0.75
     unsuccessfully
    0.72
     previously
    0.61
     unsuccessful
    0.60
    Activations Density 1.705%

    No Known Activations