© 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. 3710
    Prev
    Next
    INDEX
    Explanations

    intensifiers or emphasis words

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers and emphatic expressions related to quality and importance

    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
    halla
    -0.82
     Selection
    -0.72
    anwhile
    -0.72
    apor
    -0.72
    ulia
    -0.71
     Stability
    -0.67
    vale
    -0.66
     Estimates
    -0.66
    doi
    -0.65
    acia
    -0.65
    POSITIVE LOGITS
     ridiculous
    1.38
     stupid
    1.36
     shitty
    1.35
     hilarious
    1.34
     silly
    1.34
     egregious
    1.30
     outlandish
    1.29
     creepy
    1.29
     embarrassing
    1.29
     disgusting
    1.29
    Activations Density 0.240%

    No Known Activations