© 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
    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. 1704
    Prev
    Next
    INDEX
    Explanations

    references to physical objects related to sinking or failure

    oai_token-act-pair · gpt-3.5-turbo

    references to sinks and related contexts

    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
    avez
    -0.63
     Austral
    -0.61
    OTO
    -0.61
    Whe
    -0.60
    ordan
    -0.60
     permitting
    -0.58
     challenging
    -0.58
    PRES
    -0.57
     PRES
    -0.57
    issued
    -0.56
    POSITIVE LOGITS
     sink
    1.11
    hole
    1.06
     sinks
    1.05
    ucer
    1.01
    holes
    0.93
    maid
    0.87
    vier
    0.85
    boat
    0.83
    stream
    0.82
     sinking
    0.82
    Activations Density 0.005%

    No Known Activations