© 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. 3-RES-JB
    11. 15072
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Adelaide" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Adelaide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ages
    -0.82
    byter
    -0.77
    igation
    -0.74
    stakes
    -0.71
    gger
    -0.70
    rg
    -0.69
    rodu
    -0.68
    kefeller
    -0.68
    haul
    -0.68
    icles
    -0.67
    POSITIVE LOGITS
     Adelaide
    0.97
     Oval
    0.84
     Brisbane
    0.77
     Lumpur
    0.75
    elaide
    0.74
    shire
    0.74
     lapt
    0.70
     Rapids
    0.69
     mosqu
    0.69
     Jagu
    0.68
    Activations Density 0.004%

    No Known Activations