© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17313
    Prev
    Next
    INDEX
    Explanations

    specific mentions of legal documents or proceedings, such as "read one short document."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal authority and documents

    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
    earchers
    -0.60
     âĢº
    -0.54
    iple
    -0.54
    arij
    -0.52
    reek
    -0.52
     consists
    -0.49
     [+
    -0.48
    umbai
    -0.46
     à¨
    -0.46
     Nobel
    -0.45
    POSITIVE LOGITS
    )).
    1.28
    ?).
    1.07
    .).
    0.99
    ]).
    0.92
    ))))
    0.88
    ).
    0.87
    )))
    0.86
    )?
    0.84
    )),
    0.82
    %.
    0.82
    Activations Density 2.180%

    No Known Activations