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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    6. 5124
    Prev
    Next
    INDEX
    Explanations

    types of rocks and related terms, particularly granite, limestone, marble, and gravel

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of rock and mineral formations

    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
    >[
    -0.94
    onom
    -0.81
    ROM
    -0.80
    irts
    -0.80
    rons
    -0.80
    oresc
    -0.78
    ament
    -0.74
    INA
    -0.73
    ya
    -0.73
    ersive
    -0.73
    POSITIVE LOGITS
     granite
    1.48
     stone
    1.15
     slab
    1.14
     bould
    1.10
     stones
    1.06
     marble
    1.05
     monuments
    1.05
     quarry
    1.05
     limestone
    1.04
     quar
    1.04
    Activations Density 0.029%

    No Known Activations