© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 813
    Prev
    Next
    INDEX
    Explanations

    the specific proper noun "Mar-a-Lago."

    oai_token-act-pair · gpt-4-turbo

    phrases related to specific locations, such as properties and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    specific names of properties and notable figures associated with them

    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
     McC
    -0.72
     Dw
    -0.70
     Booker
    -0.69
     Kats
    -0.67
     Ve
    -0.66
     neut
    -0.65
    MW
    -0.64
     Vog
    -0.63
    Ve
    -0.63
    kay
    -0.62
    POSITIVE LOGITS
    xual
    0.91
    ascus
    0.87
    Lago
    0.83
    gypt
    0.80
    DragonMagazine
    0.79
    ldom
    0.78
    merce
    0.76
    )=(
    0.74
    ibia
    0.74
    artifacts
    0.73
    Activations Density 0.051%

    No Known Activations