© 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. 7-RES-JB
    11. 9559
    Prev
    Next
    INDEX
    Explanations

    specific mentions of actions or events that have "been" done

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "been" 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
    âĦ¢:
    -0.71
     Relief
    -0.71
     Awakens
    -0.71
    Must
    -0.69
    terday
    -0.67
    lies
    -0.67
    arta
    -0.67
     Wid
    -0.66
    ives
    -0.66
    odder
    -0.66
    POSITIVE LOGITS
     replaced
    0.99
     subjected
    0.98
     likened
    0.97
     taken
    0.96
     shown
    0.90
     deemed
    0.90
     upgraded
    0.89
     given
    0.89
     omitted
    0.89
     relegated
    0.88
    Activations Density 0.160%

    No Known Activations