© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3356
    Prev
    Next
    INDEX
    Explanations

    phrases related to access to services and resources, particularly in the context of healthcare and social services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to access to essential services and resources

    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
    bryce
    -1.07
    nick
    -0.80
     Photographer
    -0.76
    Plot
    -0.75
    Leaks
    -0.74
    eki
    -0.71
    puff
    -0.70
    gdala
    -0.68
    Players
    -0.68
    pload
    -0.67
    POSITIVE LOGITS
     healthcare
    1.30
     medicines
    1.28
     care
    1.27
     nutritious
    1.24
     affordable
    1.22
     services
    1.20
     medicine
    1.20
     education
    1.18
     lifes
    1.17
     prenatal
    1.17
    Activations Density 0.254%

    No Known Activations