© 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. 7-RES-JB
    11. 22956
    Prev
    Next
    INDEX
    Explanations

    information about where people live

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate where people reside

    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
    umbs
    -0.79
    elight
    -0.79
    ery
    -0.76
    oug
    -0.75
    xual
    -0.73
    anche
    -0.71
    ion
    -0.70
    aptic
    -0.66
    ional
    -0.65
    sonian
    -0.65
    POSITIVE LOGITS
     upstairs
    0.92
     vic
    0.87
     downstairs
    0.85
    lihood
    0.81
    chool
    0.78
    stead
    0.77
     indoors
    0.75
     abroad
    0.74
     paycheck
    0.74
     peacefully
    0.71
    Activations Density 0.036%

    No Known Activations