© 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. 15263
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and investigative procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal proceedings and governmental actions

    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
    âķIJ
    -0.68
    Ö¼
    -0.68
    è»
    -0.67
    vine
    -0.67
    APTER
    -0.65
    00007
    -0.63
     WAS
    -0.62
    ovo
    -0.62
    ãĤ¦ãĤ¹
    -0.62
     herself
    -0.61
    POSITIVE LOGITS
     occur
    0.95
     abound
    0.91
     prolifer
    0.79
     arise
    0.77
     propagate
    0.76
     spor
    0.75
     staged
    0.75
     converge
    0.74
     clustered
    0.74
     routinely
    0.73
    Activations Density 0.815%

    No Known Activations