© 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. 2-RES-JB
    11. 893
    Prev
    Next
    INDEX
    Explanations

    the mention of the place name "St. Louis"

    oai_token-act-pair · gpt-4-turbo

    references to the city of St. Louis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "St. Louis"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPP
    -0.72
    BOOK
    -0.72
     sparse
    -0.70
    ãĤ©
    -0.67
    TRUMP
    -0.66
     scant
    -0.65
     stringent
    -0.64
    VALUE
    -0.64
    QUEST
    -0.64
    mit
    -0.61
    POSITIVE LOGITS
     Angeles
    1.12
    sburgh
    0.98
    inois
    0.93
     Louis
    0.87
     XIV
    0.86
    shire
    0.85
     Lumpur
    0.84
     Rams
    0.84
    bourg
    0.82
    erville
    0.79
    Activations Density 0.005%

    No Known Activations