© 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
    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. 18784
    Prev
    Next
    INDEX
    Explanations

    words related to legal or military orders

    oai_token-act-pair · gpt-3.5-turbo

    references to legal commands or directives

    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
    allery
    -0.77
    Unity
    -0.77
    ãĤ©
    -0.73
    rities
    -0.73
    atism
    -0.72
     Argon
    -0.72
    vae
    -0.71
     Volks
    -0.68
     Generations
    -0.68
     Surviv
    -0.66
    POSITIVE LOGITS
    lies
    1.01
     authorizing
    0.95
     decree
    0.95
     prohibiting
    0.92
     orders
    0.89
    etary
    0.89
     issued
    0.89
     restricting
    0.88
     warrants
    0.84
     forb
    0.83
    Activations Density 0.028%

    No Known Activations