© 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. 7-RES-JB
    11. 2639
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day, Year"

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enjoy
    -0.81
    coins
    -0.80
    Edit
    -0.79
    grounds
    -0.77
    Features
    -0.68
    ETS
    -0.68
    lly
    -0.67
    End
    -0.66
    aneously
    -0.66
    ãĥ´
    -0.65
    POSITIVE LOGITS
     concerted
    1.07
     lengthy
    1.07
     brief
    1.01
     successful
    1.01
     protracted
    1.00
     spate
    0.98
     couple
    0.94
     flurry
    0.94
     rigorous
    0.94
     slight
    0.94
    Activations Density 0.114%

    No Known Activations