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. 19299
    Prev
    Next
    INDEX
    Explanations

    questions or phrases indicating inquiry or curiosity

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions or phrases that challenge the reader's understanding or perspective

    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
    igraph
    -0.87
    onz
    -0.77
    iard
    -0.75
     cig
    -0.71
    sha
    -0.68
    mone
    -0.63
    hedon
    -0.62
    ournals
    -0.60
    chairs
    -0.60
     Medals
    -0.59
    POSITIVE LOGITS
     happening
    1.01
     surprising
    0.95
     remarkable
    0.92
     interesting
    0.87
     fascinating
    0.84
     noteworthy
    0.83
     unclear
    0.83
     notable
    0.83
     happened
    0.82
     transpired
    0.80
    Activations Density 0.063%

    No Known Activations