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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20008
    Prev
    Next
    INDEX
    Explanations

    full stops at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate a conclusion or finality

    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
     disemb
    -0.80
     haul
    -0.80
     defe
    -0.76
     disarm
    -0.76
     quir
    -0.75
     brist
    -0.75
    ¥ŀ
    -0.71
     landfall
    -0.69
     bounded
    -0.68
     glim
    -0.67
    POSITIVE LOGITS
     Lastly
    1.86
     Whilst
    1.55
     Needless
    1.55
     Luckily
    1.54
     Therefore
    1.53
     Thankfully
    1.53
     Additionally
    1.52
     Unfortunately
    1.51
     Regardless
    1.51
     Furthermore
    1.50
    Activations Density 0.547%

    No Known Activations