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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4565
    Prev
    Next
    INDEX
    Explanations

    information related to corporate activities, such as company splits and financial decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of financial and corporate-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merga
    -0.81
     Erit
    -0.78
    GREEN
    -0.77
     UNHCR
    -0.76
     deport
    -0.75
     NGO
    -0.74
     Mek
    -0.73
     Refugee
    -0.72
    ï¸
    -0.70
     smugglers
    -0.70
    POSITIVE LOGITS
     AOL
    1.46
     Murdoch
    1.36
     Yahoo
    1.34
    phabet
    1.29
     Alphabet
    1.21
     Rupert
    1.17
     Mayer
    1.14
    ahoo
    1.04
     Gawker
    1.04
     Alibaba
    1.03
    Activations Density 0.245%

    No Known Activations