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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 953
    Prev
    Next
    INDEX
    Explanations

    solutions, ways, or methods for various issues or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to seeking or discovering solutions or answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    panic
    -0.80
    minus
    -0.80
    eka
    -0.72
    toggle
    -0.67
    upt
    -0.66
    oir
    -0.65
    mentioned
    -0.63
    rpm
    -0.62
    thank
    -0.62
    cour
    -0.61
    POSITIVE LOGITS
     ways
    1.35
     solutions
    1.16
     effic
    1.08
     replacements
    1.06
     alternatives
    1.05
     suitable
    0.99
     loopholes
    0.97
     optimal
    0.92
     answers
    0.91
     optimum
    0.86
    Activations Density 0.132%

    No Known Activations