© 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. 22441
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and interaction, such as interviews, phone calls, and blog posts

    oai_token-act-pair · gpt-3.5-turbo

    instances of media appearances and communication events

    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
    ãĤ¨ãĥ«
    -0.83
    opia
    -0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    balance
    -0.72
    evil
    -0.70
    mare
    -0.69
    ignty
    -0.69
    alien
    -0.68
    uid
    -0.68
    ãĥ«
    -0.67
    POSITIVE LOGITS
     seminars
    1.26
     conferences
    1.22
     interviews
    1.21
     chats
    1.16
     pamph
    1.16
     podcasts
    1.16
     workshops
    1.15
     journals
    1.14
     briefings
    1.14
     publications
    1.13
    Activations Density 0.535%

    No Known Activations