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. 0-RES-JB
    6. 7009
    Prev
    Next
    INDEX
    Explanations

    references to specific technology companies, particularly Oracle

    oai_token-act-pair · gpt-3.5-turbo

    references to the company Oracle and its stock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hern
    -0.76
    Ñģ
    -0.75
     thrust
    -0.72
     Brus
    -0.71
    ––
    -0.69
    âĹ
    -0.68
     lung
    -0.67
     brush
    -0.67
     gore
    -0.67
     chuck
    -0.65
    POSITIVE LOGITS
     Oracle
    4.14
    Oracle
    3.37
     SAP
    1.39
     MySQL
    1.22
     IBM
    1.16
     Cisco
    1.13
     Java
    1.12
     VMware
    1.11
     Atl
    1.10
    acle
    1.10
    Activations Density 0.024%

    No Known Activations