© 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. 3023
    Prev
    Next
    INDEX
    Explanations

    sources or citations

    oai_token-act-pair · gpt-3.5-turbo

    source citations or references

    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
    ties
    -0.68
    anooga
    -0.65
    bably
    -0.64
     subsequ
    -0.63
    dule
    -0.63
     indistinguishable
    -0.62
     distinguish
    -0.62
     committing
    -0.62
     scarcely
    -0.62
     rendition
    -0.61
    POSITIVE LOGITS
     http
    1.18
     Retrieved
    1.16
     Wikimedia
    1.12
     Wikipedia
    1.12
     www
    1.11
     Shutterstock
    1.08
     Ibid
    1.05
     Via
    1.04
     https
    1.02
    Wikipedia
    0.99
    Activations Density 0.066%

    No Known Activations