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. 4-RES-JB
    6. 17533
    Prev
    Next
    INDEX
    Explanations

    text related to tutorials and instructional content

    oai_token-act-pair · gpt-3.5-turbo

    references to tutorials and instructional content

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

    No Comments

    Negative Logits
    oples
    -0.73
    ternity
    -0.72
    alties
    -0.71
    och
    -0.68
    itol
    -0.67
    itizen
    -0.66
    arching
    -0.66
    eg
    -0.65
    olson
    -0.64
    oter
    -0.64
    POSITIVE LOGITS
     tutorial
    0.87
     Guide
    0.85
     Tutorial
    0.85
     tutorials
    0.84
    STEP
    0.81
     guide
    0.75
     VMware
    0.71
     Guides
    0.69
     STEP
    0.69
    utorial
    0.68
    Activations Density 0.018%

    No Known Activations