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. 18688
    Prev
    Next
    INDEX
    Explanations

    references to three-dimensional (3D) technology and related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token "<|endoftext|>"

    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
    pid
    -0.77
    76561
    -0.71
     Bulg
    -0.70
    autions
    -0.70
    olitan
    -0.70
    utory
    -0.68
    bern
    -0.67
    recomm
    -0.66
     Downing
    -0.65
    antha
    -0.65
    POSITIVE LOGITS
    imensional
    1.36
     printing
    1.10
     printer
    1.05
     printers
    1.03
     Printing
    1.02
     printed
    0.99
     Printed
    0.97
    printed
    0.91
    Mark
    0.90
     Realms
    0.89
    Activations Density 0.039%

    No Known Activations