© 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. 17713
    Prev
    Next
    INDEX
    Explanations

    terms related to complementing or adding to something already existing

    oai_token-act-pair · gpt-3.5-turbo

    connections between different concepts or elements within a context

    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
    letes
    -0.76
    encia
    -0.76
    itutes
    -0.76
    kef
    -0.75
    esters
    -0.75
    eters
    -0.72
    phans
    -0.68
    cture
    -0.66
    javascript
    -0.66
    glers
    -0.65
    POSITIVE LOGITS
     existing
    1.17
     broader
    1.14
     rest
    1.04
     usual
    1.00
     others
    0.99
     other
    0.95
     pree
    0.94
     larger
    0.94
     wider
    0.90
     actual
    0.89
    Activations Density 0.396%

    No Known Activations