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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4635
    Prev
    Next
    INDEX
    Explanations

    terms related to artificial intelligence and prediction technology

    oai_token-act-pair · gpt-3.5-turbo
    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
     refill
    -0.89
     Reload
    -0.87
    tar
    -0.85
     tub
    -0.84
     Tripoli
    -0.84
     tubing
    -0.82
     Tub
    -0.82
     cigars
    -0.81
    ð
    -0.78
    outhern
    -0.78
    POSITIVE LOGITS
     AI
    2.07
    AI
    1.74
     Artificial
    1.69
     algorithms
    1.52
     neural
    1.47
     algorith
    1.45
     artificial
    1.43
     Neural
    1.42
    ificial
    1.40
     Watson
    1.39
    Activations Density 0.428%

    No Known Activations