© 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. 8-RES-JB
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    mentions of residents in various contexts, potentially related to community or locality

    oai_token-act-pair · gpt-3.5-turbo

    references to residents in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anche
    -0.76
    Bone
    -0.72
    icer
    -0.72
    Prev
    -0.68
    enegger
    -0.67
    kefeller
    -0.65
    POS
    -0.64
    catentry
    -0.63
    SourceFile
    -0.63
    MED
    -0.62
    POSITIVE LOGITS
    hips
    1.16
    folk
    1.03
    hip
    1.01
     Residents
    0.79
     living
    0.77
     residents
    0.76
    chool
    0.72
     residing
    0.71
    ately
    0.71
    oft
    0.70
    Activations Density 0.045%

    No Known Activations