© 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 EvalsExportsinterp-engineNEWAPI 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. 5794
    Prev
    Next
    INDEX
    Explanations

    phrases related to traveling, specifically trips to different locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating travel or destination

    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
    tons
    -0.80
    rated
    -0.73
    going
    -0.72
    standing
    -0.71
     transmitted
    -0.68
     piv
    -0.67
     indicators
    -0.67
    achy
    -0.65
     flowed
    -0.64
     handled
    -0.64
    POSITIVE LOGITS
     meet
    0.89
     Uganda
    0.87
     Disneyland
    0.87
     Osaka
    0.86
    ascus
    0.86
     Liberia
    0.84
     Thailand
    0.83
     Mongolia
    0.82
     Ethiopia
    0.82
     Omaha
    0.81
    Activations Density 0.138%

    No Known Activations