© 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. 23727
    Prev
    Next
    INDEX
    Explanations

    specific page numbers referenced in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to literary or academic formats and citations

    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
     settlement
    -0.64
     perspect
    -0.64
     settled
    -0.64
     jammed
    -0.63
     controllers
    -0.61
     wiser
    -0.60
     overnight
    -0.60
     hump
    -0.59
     trave
    -0.58
     outgoing
    -0.58
    POSITIVE LOGITS
    134
    1.03
    119
    1.03
     iii
    1.02
    213
    1.01
     133
    1.01
     139
    1.01
     223
    1.01
    VII
    1.00
     153
    1.00
     131
    1.00
    Activations Density 0.056%

    No Known Activations