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. 7-RES-JB
    6. 16183
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical qualities or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to challenges and experiences in adventure and gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.84
    tarian
    -0.74
     Republican
    -0.68
    Republican
    -0.67
    Question
    -0.67
     Presbyter
    -0.66
    Correction
    -0.65
    iatus
    -0.65
    rans
    -0.65
     Presumably
    -0.64
    POSITIVE LOGITS
     unforgettable
    0.87
     customizable
    0.86
     effortlessly
    0.84
    eaturing
    0.83
     stylish
    0.80
     seamlessly
    0.80
     personalized
    0.78
     beautifully
    0.78
     thrilling
    0.76
     customize
    0.76
    Activations Density 1.165%

    No Known Activations