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. 10030
    Prev
    Next
    INDEX
    Explanations

    words related to obstacles, hindrances, and challenges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obstacles or challenges

    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
    ocene
    -0.69
    posure
    -0.67
    ults
    -0.67
    urgy
    -0.63
    itar
    -0.62
    sal
    -0.62
    odus
    -0.61
    puted
    -0.60
    liter
    -0.60
    etics
    -0.60
    POSITIVE LOGITS
     hampered
    1.26
     hindered
    1.21
     hinder
    1.12
     impede
    0.93
    nesses
    0.90
     hind
    0.88
     slowing
    0.86
     undermin
    0.84
     bothering
    0.83
     overshadowed
    0.78
    Activations Density 0.024%

    No Known Activations