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. 8-RES-JB
    6. 9379
    Prev
    Next
    INDEX
    Explanations

    names containing the word "Rich" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rich"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ËĪ
    -0.74
     pneumonia
    -0.69
     vain
    -0.65
    selves
    -0.64
    GMT
    -0.63
     Dresden
    -0.63
    conservancy
    -0.62
    sites
    -0.61
     oppos
    -0.61
    asca
    -0.60
    POSITIVE LOGITS
    mond
    1.28
    lings
    1.11
    wine
    1.10
    ochet
    1.10
    ards
    0.97
    cloth
    0.93
    ter
    0.93
    mund
    0.89
    cliffe
    0.88
    acre
    0.87
    Activations Density 0.019%

    No Known Activations