© 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. 23201
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal sentencing and judicial actions

    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
     RIS
    -0.85
    walker
    -0.78
    aucus
    -0.77
    hall
    -0.72
    Champ
    -0.72
    BLIC
    -0.70
    alter
    -0.65
    opic
    -0.65
    patch
    -0.65
    sie
    -0.63
    POSITIVE LOGITS
     sentenced
    1.13
    icts
    1.08
     convict
    0.93
     sentencing
    0.89
     inmates
    0.89
     punished
    0.88
     punishments
    0.86
     sentences
    0.86
     harshly
    0.84
    itent
    0.82
    Activations Density 0.011%

    No Known Activations