Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7794
    Prev
    Next
    INDEX
    Explanations

    phrases related to government surveillance programs

    oai_token-act-pair · gpt-3.5-turbo

    references to government surveillance and data collection programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rally
    -0.88
     Wheels
    -0.82
     Revival
    -0.79
     pist
    -0.74
     Wrest
    -0.74
     Sadd
    -0.73
     kay
    -0.73
     paddle
    -0.72
     canoe
    -0.70
     Parables
    -0.70
    POSITIVE LOGITS
     spying
    1.75
     surveillance
    1.61
    illance
    1.60
    NSA
    1.56
     eaves
    1.51
     NSA
    1.48
     spy
    1.41
     espionage
    1.40
     wiret
    1.36
     Surveillance
    1.33
    Activations Density 0.785%

    No Known Activations