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. 1-RES-JB
    6. 17464
    Prev
    Next
    INDEX
    Explanations

    acronyms related to a specific system or software, possibly related to customer relationship management (CRM)

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific category or coding structure labeled as "CR."

    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
     Sloven
    -0.79
     Ukrainian
    -0.76
     Nanto
    -0.75
    EStream
    -0.74
     Minecraft
    -0.74
    ãĥ³ãĤ¸
    -0.73
    glers
    -0.71
    uyomi
    -0.71
    nor
    -0.71
     Bunny
    -0.71
    POSITIVE LOGITS
    CR
    0.98
    anche
    0.87
    udence
    0.85
    ASH
    0.83
    isco
    0.82
    ACK
    0.81
    ashed
    0.81
    ouble
    0.78
    EDIT
    0.77
    usion
    0.76
    Activations Density 0.003%

    No Known Activations