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. 11-RES-JB
    6. 15580
    Prev
    Next
    INDEX
    Explanations

    references to open-source software and related technology

    oai_token-act-pair · gpt-3.5-turbo

    references to open-source software and related concepts

    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
    charg
    -0.88
    awed
    -0.78
    ellen
    -0.78
    oles
    -0.76
    ablishment
    -0.74
    osta
    -0.73
    hof
    -0.73
    asin
    -0.72
     Spears
    -0.71
    verages
    -0.69
    POSITIVE LOGITS
     software
    1.16
     projects
    1.06
     project
    0.97
     Software
    0.94
     SOFTWARE
    0.93
     Linux
    0.92
     libraries
    0.92
     repositories
    0.91
     Projects
    0.89
    Software
    0.89
    Activations Density 0.055%

    No Known Activations