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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4092
    Prev
    Next
    INDEX
    Explanations

    names of schools or educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.78
    pread
    -0.71
    luster
    -0.71
     excuse
    -0.66
     ple
    -0.65
    acebook
    -0.65
     goddamn
    -0.64
     darn
    -0.64
     favourable
    -0.64
    erella
    -0.63
    POSITIVE LOGITS
     Ltd
    1.04
     Cooperative
    0.98
     LLC
    0.94
     Farms
    0.93
     Solutions
    0.89
     Associates
    0.88
     LLP
    0.87
     Laboratories
    0.87
     Partners
    0.85
     Enterprises
    0.85
    Activations Density 0.479%

    No Known Activations