© 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. 9-RES-JB
    11. 14802
    Prev
    Next
    INDEX
    Explanations

    terms related to fighting or combatting various issues and challenges

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented words related to various global issues and conflicts

    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
    ittal
    -0.77
    astery
    -0.69
    ĸļ
    -0.68
    Begin
    -0.68
    DragonMagazine
    -0.67
    subject
    -0.66
     announ
    -0.65
    ETHOD
    -0.65
    \\\\\\\\
    -0.64
    Purchase
    -0.63
    POSITIVE LOGITS
     corruption
    1.18
     extremism
    1.13
     terrorism
    1.13
     homophobia
    1.08
     obesity
    1.06
     racism
    1.05
     piracy
    1.03
     bullying
    1.03
     poverty
    1.01
     injustice
    1.00
    Activations Density 0.188%

    No Known Activations