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. 1-RES-JB
    6. 1675
    Prev
    Next
    INDEX
    Explanations

    phrases related to motivation and inspiration

    oai_token-act-pair · gpt-3.5-turbo

    words related to motivation and enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arat
    -0.73
     Rabbit
    -0.71
     DX
    -0.69
     dod
    -0.63
     Dee
    -0.63
     JP
    -0.62
    bit
    -0.62
     Plaza
    -0.61
    den
    -0.60
    jab
    -0.57
    POSITIVE LOGITS
    ivated
    1.50
    ivating
    1.15
    ivation
    1.03
    veyard
    0.99
    itiveness
    0.84
    theless
    0.84
    CLASSIFIED
    0.83
    urally
    0.81
    zsche
    0.81
    atically
    0.80
    Activations Density 0.024%

    No Known Activations