© 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. 11-RES-JB
    11. 23805
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and exclamations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional reactions, particularly positive or humorous sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.75
    âĢij
    -0.74
    verning
    -0.70
    idis
    -0.68
    adata
    -0.66
     ÂŃ
    -0.64
     unden
    -0.63
    isively
    -0.62
     Gutenberg
    -0.62
    ocratic
    -0.61
    POSITIVE LOGITS
     :)
    1.61
     haha
    1.58
     ;)
    1.55
     lol
    1.50
     :(
    1.49
     XD
    1.38
     tho
    1.33
     !!
    1.30
     :-)
    1.29
    !!
    1.28
    Activations Density 0.424%

    No Known Activations