© 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. 10-RES-JB
    11. 14102
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    legal references to statutes and acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.82
    earcher
    -0.71
    alon
    -0.71
     dots
    -0.70
    uers
    -0.70
    blers
    -0.69
     mole
    -0.67
     studios
    -0.67
     specialists
    -0.67
     scouts
    -0.66
    POSITIVE LOGITS
     Act
    1.54
     statute
    1.43
     Regulations
    1.41
     statutes
    1.38
     Constitution
    1.37
     treaty
    1.36
     constitution
    1.36
     Treaty
    1.36
     Amendments
    1.35
     treaties
    1.35
    Activations Density 0.372%

    No Known Activations