© 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. 11-RES-JB
    11. 21801
    Prev
    Next
    INDEX
    Explanations

    descriptions of real estate properties

    oai_token-act-pair · gpt-3.5-turbo

    details related to construction and development projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wrong
    -0.78
    yet
    -0.74
     cries
    -0.71
     scares
    -0.71
    Yesterday
    -0.69
     lately
    -0.69
    uddenly
    -0.68
     fright
    -0.68
     complains
    -0.68
    dad
    -0.67
    POSITIVE LOGITS
     totaling
    0.98
     comprising
    0.96
     preferably
    0.84
     ideally
    0.84
     hereafter
    0.84
     incorporating
    0.83
     slated
    0.83
     jointly
    0.83
     integrating
    0.82
     encomp
    0.81
    Activations Density 0.593%

    No Known Activations