© 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. 4396
    Prev
    Next
    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    prominent names of individuals, likely related to news or media

    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
    stood
    -0.78
     successors
    -0.69
     conferences
    -0.68
    netflix
    -0.65
     dracon
    -0.65
     Directors
    -0.65
     fame
    -0.64
     USSR
    -0.64
     Twin
    -0.63
     Eleven
    -0.62
    POSITIVE LOGITS
    utterstock
    0.97
    Photo
    0.80
     Shutterstock
    0.75
    photo
    0.75
    ©¶æ
    0.74
    ource
    0.72
    rique
    0.70
    obal
    0.69
    Courtesy
    0.69
    verett
    0.68
    Activations Density 0.168%

    No Known Activations