© 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. 10-RES-JB
    11. 12815
    Prev
    Next
    INDEX
    Explanations

    mentions of the spacecraft named Rosetta

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORN
    -0.66
     Countdown
    -0.64
    ulhu
    -0.62
    Reloaded
    -0.62
     Hunger
    -0.61
    redit
    -0.61
     setback
    -0.59
    ered
    -0.59
     Predator
    -0.58
    },"
    -0.57
    POSITIVE LOGITS
    coe
    1.35
    etta
    1.33
    enthal
    1.12
    ario
    1.10
    acea
    1.08
    anne
    1.06
    lyn
    1.03
    atom
    1.03
    alez
    1.02
    kies
    1.00
    Activations Density 0.022%

    No Known Activations