© 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. 11-RES-JB
    11. 1717
    Prev
    Next
    INDEX
    Explanations

    phrases related to reversal or change in a situation

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to state changes or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ici
    -0.69
    heid
    -0.64
    alde
    -0.63
    olor
    -0.61
    iosyncr
    -0.58
     Noon
    -0.57
    esson
    -0.56
    ilon
    -0.55
    Ĥª
    -0.55
    hey
    -0.54
    POSITIVE LOGITS
     down
    2.43
    down
    2.05
     Down
    1.81
    Down
    1.79
     downs
    1.66
    downs
    1.66
     DOWN
    1.57
    DOWN
    1.38
    tered
    1.12
     Downs
    1.01
    Activations Density 0.484%

    No Known Activations