© 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. 18646
    Prev
    Next
    INDEX
    Explanations

    phrases related to unbundling and unburdening processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "unb-" and related terms

    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
    ãĥ³ãĤ¸
    -0.77
     Trilogy
    -0.71
     Pros
    -0.70
     Lawn
    -0.69
     partName
    -0.68
    =#
    -0.67
    IAL
    -0.67
    =-=-=-=-
    -0.67
     Vag
    -0.67
     Occupations
    -0.66
    POSITIVE LOGITS
     unb
    1.00
    ishop
    0.96
    untu
    0.94
    odied
    0.93
    ruary
    0.93
    ilingual
    0.90
    bent
    0.89
    odies
    0.88
    anked
    0.87
     challeng
    0.87
    Activations Density 0.013%

    No Known Activations