© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8376
    Prev
    Next
    INDEX
    Explanations

    adjectives related to things that are interesting or captivating

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fascinating" and its synonyms, indicating a focus on intriguing topics or ideas

    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
    ache
    -0.78
    alf
    -0.65
     substitute
    -0.65
     default
    -0.62
     admin
    -0.62
    AA
    -0.62
    Aid
    -0.61
     employee
    -0.61
     defaults
    -0.61
     Action
    -0.61
    POSITIVE LOGITS
     fascinating
    3.21
     intriguing
    2.21
     fascinated
    1.78
     delightful
    1.72
     thrilling
    1.71
     tantal
    1.52
     marvelous
    1.52
     remarkable
    1.52
     interesting
    1.51
     breathtaking
    1.48
    Activations Density 0.032%

    No Known Activations