© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2771
    Prev
    Next
    INDEX
    Explanations

    phrases related to business acquisitions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to acquisitions and mergers in a corporate context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aturdays
    -0.85
    ItemImage
    -0.85
    pmwiki
    -0.84
    aucuses
    -0.84
    ItemThumbnailImage
    -0.84
    ierre
    -0.81
    è¯
    -0.78
    xual
    -0.77
    ////
    -0.77
    ptoms
    -0.77
    POSITIVE LOGITS
     Panasonic
    1.15
     Alibaba
    1.14
     Warner
    1.12
     Coca
    1.11
     Microsoft
    1.09
     Sony
    1.08
     Hew
    1.07
     Activision
    1.07
     Deutsche
    1.06
     Comcast
    1.06
    Activations Density 0.372%

    No Known Activations