© 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. 1-RES-JB
    11. 22936
    Prev
    Next
    INDEX
    Explanations

    words related to choices or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possibilities or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aging
    -0.85
    ursed
    -0.75
    ages
    -0.73
    bing
    -0.71
    izing
    -0.71
    agement
    -0.71
    abeth
    -0.67
    izes
    -0.65
    ization
    -0.64
    ize
    -0.63
    POSITIVE LOGITS
    soever
    1.19
    ãĥ¯ãĥ³
    0.89
    yip
    0.83
    Whether
    0.82
     Whether
    0.82
    whether
    0.75
    aminer
    0.70
    GGGGGGGG
    0.68
     reluct
    0.67
    ornia
    0.66
    Activations Density 0.015%

    No Known Activations