© 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. 11376
    Prev
    Next
    INDEX
    Explanations

    references to the TV show "Orange Is the New Black"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Orange" in various contexts, particularly related to the county and its associated topics

    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
    ted
    -0.90
    rets
    -0.82
    fare
    -0.81
    Ö¼
    -0.81
    sonian
    -0.76
    stood
    -0.74
    ts
    -0.72
    atted
    -0.70
    akable
    -0.70
    isSpecialOrderable
    -0.69
    POSITIVE LOGITS
     Blossom
    1.15
     Peel
    1.05
    vale
    1.05
     peel
    1.04
     juice
    1.03
     Juice
    1.01
     Crush
    0.95
     cones
    0.84
     County
    0.82
    cone
    0.72
    Activations Density 0.025%

    No Known Activations