© 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. 7-RES-JB
    11. 23022
    Prev
    Next
    INDEX
    Explanations

    the word "Brand" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attendant
    -0.81
    pmwiki
    -0.77
    ORPG
    -0.65
     cumbers
    -0.65
    fortunately
    -0.65
    ĺħ
    -0.62
    ursion
    -0.62
    ITED
    -0.61
    ired
    -0.60
     streamed
    -0.60
    POSITIVE LOGITS
    enburg
    1.21
    ing
    0.94
    stown
    0.91
    enberg
    0.91
    opher
    0.87
    olph
    0.83
    hoff
    0.82
    eering
    0.81
    zen
    0.79
    enstein
    0.78
    Activations Density 0.031%

    No Known Activations