© 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. 0-RES-JB
    11. 6318
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific missions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific "Mission" titles, particularly focusing on "Mission 9" and "Mission 5."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inherit
    -0.78
     clot
    -0.74
    iot
    -0.69
     alle
    -0.68
     ow
    -0.68
     ank
    -0.68
     smoot
    -0.68
    rod
    -0.67
     deter
    -0.65
    Der
    -0.65
    POSITIVE LOGITS
     Mission
    3.91
    Mission
    2.84
     Missions
    2.61
     mission
    2.15
     missions
    1.90
    mission
    1.40
     missionary
    1.32
    ISSION
    1.28
     missionaries
    1.21
     Expedition
    1.20
    Activations Density 0.018%

    No Known Activations