© 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 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. 20796
    Prev
    Next
    INDEX
    Explanations

    locations or establishments for different types of companies or businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to the presence or establishment of stores in specific locations

    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
     inval
    -0.73
    tre
    -0.71
     lodged
    -0.69
    CLASSIFIED
    -0.65
    CHA
    -0.64
    0000000000000000
    -0.64
    catentry
    -0.63
    ¿½
    -0.62
    LOG
    -0.62
    wagon
    -0.61
    POSITIVE LOGITS
     lieu
    1.33
     accordance
    1.27
     conjunction
    1.17
    effic
    1.07
    efficiency
    1.05
    clusions
    1.04
     vitro
    1.04
    roads
    1.01
    humane
    0.96
     unison
    0.95
    Activations Density 0.458%

    No Known Activations