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. 7-RES-JB
    6. 16837
    Prev
    Next
    INDEX
    Explanations

    random letters and symbols that do not seem to form coherent words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or unusual formatting and encoding characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gad
    -0.81
    anwhile
    -0.77
    wagen
    -0.76
     Peb
    -0.75
     scattering
    -0.73
    nesday
    -0.70
     Berm
    -0.69
     dispers
    -0.68
     messenger
    -0.67
     wink
    -0.67
    POSITIVE LOGITS
    º
    1.34
    ¹
    1.27
    £
    1.21
    Į
    1.16
    ®
    1.13
    į
    1.13
    ¬
    1.11
    ı
    1.09
    ª
    1.09
    Ī
    1.07
    Activations Density 0.100%

    No Known Activations