© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 7448
    Prev
    Next
    INDEX
    Explanations

    instances of locations or events being visited

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "visited."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rats
    -0.81
    corn
    -0.75
    uscript
    -0.73
    dry
    -0.72
    nom
    -0.71
    assi
    -0.71
    oil
    -0.70
    boa
    -0.69
    absolute
    -0.68
    smart
    -0.67
    POSITIVE LOGITS
     visited
    1.13
     visits
    0.95
     visiting
    0.92
    ãĥ¼ãĥĨ
    0.89
     abroad
    0.87
    代
    0.83
     Disneyland
    0.75
     Tours
    0.75
     visit
    0.74
    shire
    0.72
    Activations Density 0.014%

    No Known Activations