© 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
    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. 2195
    Prev
    Next
    INDEX
    Explanations

    locations on a map or geographical descriptions

    oai_token-act-pair · gpt-3.5-turbo

    geographical directions and locations

    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
    ======
    -0.73
    alist
    -0.73
    neys
    -0.71
    Money
    -0.71
    ulative
    -0.70
    Craft
    -0.69
    apply
    -0.69
    events
    -0.67
    uzz
    -0.67
    inarily
    -0.67
    POSITIVE LOGITS
    most
    1.67
     hemisphere
    1.25
     portion
    1.17
     part
    1.13
     tip
    1.13
     suburbs
    1.11
     edge
    1.10
     reaches
    1.06
     extrem
    1.05
     slopes
    1.04
    Activations Density 0.062%

    No Known Activations