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. 2-RES-JB
    6. 10581
    Prev
    Next
    INDEX
    Explanations

    references to wealthy individuals or families

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth and being wealthy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.95
    IENCE
    -0.83
    OUT
    -0.82
    STD
    -0.72
    FY
    -0.71
    2019
    -0.69
    OPE
    -0.68
    soDeliveryDate
    -0.68
    é¾įå¥ij士
    -0.68
     Dresden
    -0.68
    POSITIVE LOGITS
     richer
    1.11
    ened
    0.91
    hardt
    0.88
     rich
    0.86
    ochet
    0.84
    esse
    0.82
     enough
    0.80
    rich
    0.80
    ening
    0.76
    lings
    0.76
    Activations Density 0.012%

    No Known Activations