© 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. 4-RES-JB
    11. 7431
    Prev
    Next
    INDEX
    Explanations

    words related to non-standard or unconventional practices, often in the context of different categories such as immigrants, military, food, religion, and state

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with categories and classifications, particularly around non-conformity and specific identity groups

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

    No Comments

    Negative Logits
    CHAT
    -0.78
    adder
    -0.72
    AMS
    -0.67
    Dialogue
    -0.66
    oglu
    -0.66
    MAC
    -0.64
    wagen
    -0.64
    brance
    -0.64
    isu
    -0.61
    frey
    -0.61
    POSITIVE LOGITS
    theless
    0.96
    withstanding
    0.85
    ensical
    0.82
    existent
    0.78
    istant
    0.77
     whatsoever
    0.77
    ensable
    0.76
    igenous
    0.76
     nor
    0.75
    roleum
    0.73
    Activations Density 0.072%

    No Known Activations