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. 11-RES-JB
    6. 3039
    Prev
    Next
    INDEX
    Explanations

    descriptions of family background and upbringing

    oai_token-act-pair · gpt-3.5-turbo

    references to familial and socioeconomic backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsi
    -0.87
    loads
    -0.76
     Extensions
    -0.73
     deputies
    -0.72
    Events
    -0.69
    immers
    -0.67
    charges
    -0.67
    rays
    -0.67
     trademarks
    -0.66
     negotiators
    -0.65
    POSITIVE LOGITS
     household
    1.09
     dysfunctional
    1.05
     ghetto
    1.01
     convent
    0.99
     households
    0.99
     abusive
    0.99
     privileged
    0.97
     society
    0.97
     suburb
    0.96
     rural
    0.95
    Activations Density 0.235%

    No Known Activations