© 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. 11-RES-JB
    11. 22346
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities or objects

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" 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
     Accessed
    -0.71
    frey
    -0.68
     respectively
    -0.68
    illion
    -0.67
    SPONSORED
    -0.66
     furthermore
    -0.65
    meg
    -0.64
    iband
    -0.63
     anew
    -0.63
    isin
    -0.62
    POSITIVE LOGITS
     rest
    1.42
     originals
    1.29
     others
    1.25
     usual
    1.18
     ones
    1.16
     previous
    1.13
     norm
    1.10
     preceding
    1.03
     original
    1.02
     typical
    0.99
    Activations Density 0.238%

    No Known Activations