© 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 EvalsExportsAPI 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. 980
    Prev
    Next
    INDEX
    Explanations

    references to chat-related content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of chat-related concepts and contexts

    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
    ©¶æ
    -0.73
    CVE
    -0.68
    ĻĤ
    -0.65
    profit
    -0.63
     graded
    -0.59
     Flavoring
    -0.58
     Goods
    -0.57
    engeance
    -0.54
     Aven
    -0.54
     consec
    -0.54
    POSITIVE LOGITS
    anooga
    1.33
    bots
    1.09
    rooms
    1.01
    room
    1.01
    ters
    0.91
    acters
    0.87
     rooms
    0.87
     chat
    0.85
    ting
    0.82
     chats
    0.81
    Activations Density 0.030%

    No Known Activations