© 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. 8-RES-JB
    11. 7732
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases that relate to legal or regulatory burdens and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reckoned
    -0.78
    ovies
    -0.71
     downed
    -0.69
    die
    -0.69
     gorgeous
    -0.66
     Odin
    -0.66
     worshipped
    -0.65
     smashed
    -0.65
     Travels
    -0.65
     snapped
    -0.64
    POSITIVE LOGITS
     safeguards
    1.07
     discretion
    0.95
    Recommend
    0.95
     jurisd
    0.93
     assurances
    0.92
     clauses
    0.91
     litigation
    0.87
     confidentiality
    0.85
     Plaint
    0.84
     provisions
    0.83
    Activations Density 0.798%

    No Known Activations