© 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. 10-RES-JB
    11. 16963
    Prev
    Next
    INDEX
    Explanations

    words related to location, including specific places and directions

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [+
    -0.88
    ?]
    -0.75
     tho
    -0.74
     XD
    -0.74
     [/
    -0.73
     Secondly
    -0.69
    Therefore
    -0.67
     afore
    -0.67
     =>
    -0.67
    ]"
    -0.67
    POSITIVE LOGITS
     unmist
    1.12
     strikingly
    0.96
     decidedly
    0.93
     breathtaking
    0.87
     conspic
    0.87
     startling
    0.87
     undeniably
    0.87
     vividly
    0.86
     remarkably
    0.86
     unrem
    0.84
    Activations Density 0.894%

    No Known Activations