Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17905
    Prev
    Next
    INDEX
    Explanations

    terms related to different professions and activities, such as casting, politics, writing, and reincarnation

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and phrases related to academic and social concepts

    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
     Rasmussen
    -0.65
     sergeant
    -0.64
     Observer
    -0.62
     dotted
    -0.60
     skipped
    -0.60
     Torn
    -0.59
     nicknamed
    -0.59
     Sheriff
    -0.57
     alarmed
    -0.57
     Sergeant
    -0.57
    POSITIVE LOGITS
    iculture
    1.43
    arenthood
    1.33
    odynamics
    1.29
    thood
    1.24
    ogenesis
    1.20
    anship
    1.16
    itism
    1.13
    ativity
    1.12
    rification
    1.11
    iquette
    1.10
    Activations Density 0.585%

    No Known Activations