© 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. 9-RES-JB
    11. 8624
    Prev
    Next
    INDEX
    Explanations

    texts related to relocating or moving to a new location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "move to" followed by a location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etta
    -0.66
    Ĥª
    -0.66
    ¿½
    -0.64
    ¼
    -0.63
    stellar
    -0.62
    ingly
    -0.62
    DragonMagazine
    -0.61
    IJ
    -0.61
    ighth
    -0.59
    Supported
    -0.59
    POSITIVE LOGITS
     accommodate
    0.88
     eliminate
    0.79
     capitalize
    0.79
     relieve
    0.79
     safer
    0.77
     improve
    0.76
     Tycoon
    0.76
     suburb
    0.76
     occupy
    0.75
     appease
    0.74
    Activations Density 0.110%

    No Known Activations