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. 10-RES-JB
    6. 14793
    Prev
    Next
    INDEX
    Explanations

    occurrences where a statement is completed or emphasized

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satell
    -0.95
     carbohyd
    -0.87
     challeng
    -0.87
     millenn
    -0.84
    ¥ŀ
    -0.82
     charact
    -0.81
     strugg
    -0.81
     neighb
    -0.78
     transitions
    -0.78
     tremend
    -0.78
    POSITIVE LOGITS
     Presumably
    1.65
     Apparently
    1.64
     Basically
    1.52
     Which
    1.51
     Seems
    1.47
     Nope
    1.46
     Hmm
    1.42
     Sounds
    1.42
     Yep
    1.41
     Turns
    1.41
    Activations Density 0.565%

    No Known Activations