© 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. 0-RES-JB
    11. 20500
    Prev
    Next
    INDEX
    Explanations

    terms related to fun or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Fun" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stri
    -0.79
    eded
    -0.67
     undermine
    -0.66
     sectors
    -0.65
     weaken
    -0.65
     blacklist
    -0.65
     sharply
    -0.65
    urer
    -0.65
     perceive
    -0.64
     perce
    -0.63
    POSITIVE LOGITS
     Fun
    3.74
    Fun
    2.82
    fun
    2.48
     FUN
    2.09
     fun
    1.79
    FUN
    1.65
     Funk
    1.30
     Funny
    1.18
     funeral
    1.15
     Awesome
    1.06
    Activations Density 0.017%

    No Known Activations