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. 3-RES-JB
    6. 1639
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal emotions or reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fragment
    -0.67
     foreground
    -0.67
     advisers
    -0.67
    ä¹ĭ
    -0.66
    utterstock
    -0.66
     sophistic
    -0.66
     exclusion
    -0.66
     telephone
    -0.66
     precip
    -0.65
     fraught
    -0.64
    POSITIVE LOGITS
     ;)
    1.19
     :)
    1.18
     haha
    1.10
     :(
    1.03
    lol
    1.00
    !!!!!
    0.97
     didnt
    0.96
     dont
    0.94
     lol
    0.94
     :-)
    0.94
    Activations Density 0.658%

    No Known Activations