Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 18252
    Prev
    Next
    INDEX
    Explanations

    terms related to demographics and characteristics of people or objects such as ethnicity, income, educational attainment, and design efficiency

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to socioeconomic indicators and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zan
    -0.85
    scrib
    -0.75
    byter
    -0.74
    unic
    -0.72
    ©¶æ
    -0.71
    eday
    -0.71
    utory
    -0.71
    married
    -0.71
    nik
    -0.70
    irez
    -0.70
    POSITIVE LOGITS
     attractiveness
    1.14
     longevity
    1.13
     viability
    1.12
     aesthetics
    1.09
     quality
    1.08
     responsiveness
    1.06
     perceptions
    1.04
     productivity
    1.04
     accessibility
    1.03
     competitiveness
    1.03
    Activations Density 0.322%

    No Known Activations