© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 15760
    Prev
    Next
    INDEX
    Explanations

    keywords related to diverse topics from spider species to military groups

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebin
    -0.77
    done
    -0.73
    pring
    -0.68
    OME
    -0.68
    idious
    -0.68
     Ù
    -0.62
    ystem
    -0.61
    peed
    -0.61
    etting
    -0.61
     dstg
    -0.60
    POSITIVE LOGITS
     specializes
    1.15
     dominates
    1.15
     combines
    1.13
     mixes
    1.11
     encompasses
    1.08
     emphasizes
    1.08
     promotes
    1.07
     spans
    1.07
     accompanies
    1.07
     resembles
    1.06
    Activations Density 0.159%

    No Known Activations