© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 9282
    Prev
    Next
    INDEX
    Explanations

    positive sentiment words or phrases with a hint of flirtation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disbelief or surprise

    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
    verning
    -0.75
     principally
    -0.69
     Infrastructure
    -0.67
     outset
    -0.64
    ãĥ¼ãĥĨ
    -0.64
     broadly
    -0.64
     stewards
    -0.63
     initiatives
    -0.62
     automobile
    -0.61
     policymakers
    -0.61
    POSITIVE LOGITS
     lol
    1.17
     fuckin
    1.15
     fucking
    1.14
    eeee
    1.14
     gonna
    1.11
     haha
    1.11
     wanna
    1.09
     ya
    1.05
     kinda
    1.05
     fuck
    1.05
    Activations Density 0.977%

    No Known Activations