© 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. 11-RES-JB
    11. 4805
    Prev
    Next
    INDEX
    Explanations

    words related to locations, possibly focusing on specific types of locations or features of the locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bot" or related to "bot" in various contexts

    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
    SOURCE
    -0.75
     proportions
    -0.66
     versa
    -0.59
     motives
    -0.57
    vier
    -0.57
     relative
    -0.56
    HAM
    -0.55
     Boat
    -0.55
     nature
    -0.55
    ONSORED
    -0.55
    POSITIVE LOGITS
    rans
    1.11
    assium
    1.09
    tery
    1.08
    opia
    1.07
    eca
    1.04
    opic
    0.99
    zeb
    0.98
    TL
    0.96
    ting
    0.96
    rophic
    0.94
    Activations Density 0.057%

    No Known Activations