© 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. 10-RES-JB
    11. 21702
    Prev
    Next
    INDEX
    Explanations

    publicly available information or documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the public availability of information or documents

    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
    uko
    -0.68
    oglu
    -0.66
    worker
    -0.61
    involved
    -0.60
    osi
    -0.60
    orio
    -0.60
     transpl
    -0.59
    gencies
    -0.58
     crafts
    -0.58
    ggles
    -0.57
    POSITIVE LOGITS
     publicly
    1.34
     online
    1.08
     anonymously
    1.08
     electronically
    1.03
     aloud
    1.00
    onym
    0.93
     orally
    0.92
    online
    0.90
     WikiLeaks
    0.89
     widely
    0.87
    Activations Density 0.359%

    No Known Activations