© 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. 10-RES-JB
    11. 10589
    Prev
    Next
    INDEX
    Explanations

    options and choices that involve decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of choices or options presented in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rote
    -0.86
    metadata
    -0.81
    rites
    -0.74
    sted
    -0.67
    ãĥĥ
    -0.67
    icans
    -0.67
    issance
    -0.67
    estones
    -0.65
    Ŀ
    -0.65
    wordpress
    -0.65
    POSITIVE LOGITS
     either
    1.15
    Either
    1.15
     Either
    1.13
    either
    1.03
    Option
    0.94
     whichever
    0.84
     Option
    0.83
     option
    0.82
     opting
    0.79
     choosing
    0.78
    Activations Density 0.234%

    No Known Activations