© 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. 4-RES-JB
    11. 20735
    Prev
    Next
    INDEX
    Explanations

    phrases related to the function of objects or systems

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "function" with various contextual meanings

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

    No Comments

    Negative Logits
     Jed
    -0.75
     Solo
    -0.72
     Fif
    -0.72
     Hemp
    -0.72
    CU
    -0.67
    cott
    -0.64
     Crus
    -0.63
     Harriet
    -0.63
     millenn
    -0.62
     Colleges
    -0.62
    POSITIVE LOGITS
    ional
    0.96
    ioned
    0.88
    xes
    0.87
    abilities
    0.86
    ative
    0.86
     functions
    0.85
    alities
    0.85
    inic
    0.83
    ivity
    0.82
    aries
    0.79
    Activations Density 0.017%

    No Known Activations