© 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. 2-RES-JB
    11. 4300
    Prev
    Next
    INDEX
    Explanations

    keywords related to drugs and specific names such as "cocaine", "cucumber", "cronenberg", and "garcía"

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to substances and personal names associated with indulgence or privilege

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posts
    -0.71
     Pax
    -0.71
    DragonMagazine
    -0.70
    erness
    -0.70
     Tycoon
    -0.68
    uyomi
    -0.67
     Gemini
    -0.67
    holes
    -0.67
    POST
    -0.66
    ĪĴ
    -0.65
    POSITIVE LOGITS
    keye
    1.16
    onduct
    1.13
    keyes
    1.04
    urses
    0.99
    ategor
    0.95
    ursed
    0.92
    kered
    0.91
    ursor
    0.90
    redited
    0.89
    rypted
    0.88
    Activations Density 0.021%

    No Known Activations