© 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. 4-RES-JB
    11. 10118
    Prev
    Next
    INDEX
    Explanations

    names of specific locations, particularly "Rochester"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Rochester

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

    No Comments

    Negative Logits
    catentry
    -0.74
    iyah
    -0.72
    arial
    -0.70
    chens
    -0.68
    itarian
    -0.66
    policy
    -0.65
    aylor
    -0.64
    tight
    -0.64
    rus
    -0.63
    tering
    -0.62
    POSITIVE LOGITS
    shire
    1.08
     Rochester
    0.99
     Armory
    0.83
     Borough
    0.81
    issance
    0.81
     Roads
    0.74
     Falls
    0.71
    joy
    0.69
    ington
    0.68
     Hills
    0.66
    Activations Density 0.013%

    No Known Activations