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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    6. 4054
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to computer hardware

    oai_token-act-pair · gpt-3.5-turbo

    references to laptop specifications and types

    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
     Adin
    -0.92
     promoters
    -0.88
     rab
    -0.86
     promoter
    -0.84
     corrid
    -0.83
     Mexicans
    -0.81
    ETHOD
    -0.80
     elephants
    -0.79
     measles
    -0.77
     rh
    -0.76
    POSITIVE LOGITS
     Lenovo
    1.94
     MacBook
    1.93
     laptop
    1.80
     laptops
    1.77
     Chromebook
    1.68
     Dell
    1.66
     notebook
    1.62
     Acer
    1.61
     Asus
    1.60
     Surface
    1.57
    Activations Density 0.324%

    No Known Activations