© 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. 2-RES-JB
    11. 17818
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms related to agreements or negotiations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal plea agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poll
    -0.79
    orians
    -0.75
    lav
    -0.69
    miah
    -0.67
     Frankfurt
    -0.65
    twitter
    -0.65
    7601
    -0.65
    ifa
    -0.65
    bj
    -0.64
     Ancients
    -0.63
    POSITIVE LOGITS
     plea
    1.12
     plead
    1.06
     pled
    0.97
     bargain
    0.95
     barg
    0.88
     pleading
    0.87
     pleas
    0.86
     pleaded
    0.84
     indictment
    0.76
    pload
    0.73
    Activations Density 0.005%

    No Known Activations