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

    Neuronpedia

    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. 9-RES-JB
    11. 14149
    Prev
    Next
    INDEX
    Explanations

    terms related to technical issues or challenges, such as malfunctions, missed timetables, and cracked encryption networks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of network security concerns and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tv
    -0.55
    ropolitan
    -0.54
     friendships
    -0.53
    iership
    -0.52
    morrow
    -0.50
     resear
    -0.50
     collaborations
    -0.47
     Journals
    -0.47
     Nobel
    -0.47
     democracies
    -0.47
    POSITIVE LOGITS
     improperly
    0.63
     inappropriately
    0.61
     incorrectly
    0.60
     breached
    0.59
    rompt
    0.59
     violated
    0.59
     undet
    0.58
     prematurely
    0.57
    instead
    0.57
     abruptly
    0.57
    Activations Density 1.526%

    No Known Activations