© 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. 8-RES-JB
    11. 22671
    Prev
    Next
    INDEX
    Explanations

    information related to events or announcements, such as workshops, classes, or donations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to providing information and instructions for events and donations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Laughs
    -0.69
     sucker
    -0.64
     overpowered
    -0.64
     damn
    -0.63
     illusion
    -0.62
     mediocre
    -0.62
    Ö¼
    -0.62
     Kuro
    -0.62
    Damn
    -0.62
    Ĥİ
    -0.61
    POSITIVE LOGITS
     broch
    1.07
     Membership
    1.07
     Contact
    1.05
    Contact
    1.04
     Submit
    0.99
     contact
    0.99
     Email
    0.98
     inquiries
    0.94
     Visit
    0.93
     Schedule
    0.91
    Activations Density 0.647%

    No Known Activations