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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 9886
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and superlatives

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal preference or favorite things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oros
    -0.60
    hai
    -0.58
    icans
    -0.56
    etta
    -0.55
    elf
    -0.55
     revise
    -0.55
    ulent
    -0.54
    oris
    -0.54
    ãĤ¼
    -0.53
     resumes
    -0.53
    POSITIVE LOGITS
     ones
    0.91
     standout
    0.80
     favorites
    0.80
     none
    0.77
    liest
    0.76
     singled
    0.74
     hardest
    0.74
     favourites
    0.74
    none
    0.72
    Probably
    0.71
    Activations Density 0.554%

    No Known Activations