© 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. 17504
    Prev
    Next
    INDEX
    Explanations

    medical conditions and physical descriptions of injuries

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and their associations with various contexts

    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
     attRot
    -0.70
    pires
    -0.64
    OULD
    -0.54
    "))
    -0.53
    ":[
    -0.52
    ":{"
    -0.52
    )).
    -0.50
    pired
    -0.48
     isEnabled
    -0.48
    ãĥĺ
    -0.48
    POSITIVE LOGITS
     while
    0.92
     whereas
    0.89
     during
    0.85
     and
    0.85
     when
    0.85
     whenever
    0.85
     whilst
    0.83
     throughout
    0.80
     because
    0.77
     insofar
    0.76
    Activations Density 1.199%

    No Known Activations