© 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. 15942
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibility and management

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to authority, responsibility, and societal norms

    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
    Nich
    -0.69
    ãĥ¼ãĥĨ
    -0.68
    Universal
    -0.65
    Bride
    -0.64
    Repeat
    -0.63
     Vaugh
    -0.62
    Course
    -0.62
    Materials
    -0.62
    Mobil
    -0.61
    Western
    -0.61
    POSITIVE LOGITS
     english
    0.88
    ername
    0.72
     dont
    0.72
     doesnt
    0.71
     tho
    0.67
     flair
    0.67
     didnt
    0.67
     sd
    0.65
     bud
    0.64
     gonna
    0.64
    Activations Density 0.356%

    No Known Activations