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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9183
    Prev
    Next
    INDEX
    Explanations

    characteristics or attributes that are being searched for in a person or situation, such as athleticism, talent, support, motivation, flexibility, size, resources, experience, acting chops, connections, versatility, fortitude, and confidence

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with support, resources, and attributes related to success or capability

    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
    adow
    -0.77
    Release
    -0.71
    edIn
    -0.70
    WARE
    -0.68
     VIDEOS
    -0.67
    EE
    -0.64
    Ĥª
    -0.64
    iffe
    -0.63
    outube
    -0.62
     corrid
    -0.61
    POSITIVE LOGITS
    liest
    1.23
    iest
    1.14
     necessary
    1.13
     requisite
    1.04
    same
    1.04
     equivalent
    1.02
     needed
    0.98
     required
    0.90
    hest
    0.89
    est
    0.89
    Activations Density 0.399%

    No Known Activations