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. 7-RES-JB
    6. 12897
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities and plots

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to planning and conspiratorial activities, particularly those involving violence or crime

    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
     applause
    -0.74
     wip
    -0.73
    answer
    -0.72
     Pebble
    -0.70
     reviewer
    -0.68
     parity
    -0.66
     sque
    -0.66
     clarity
    -0.66
     sequ
    -0.66
    annel
    -0.65
    POSITIVE LOGITS
     smuggling
    1.18
     jihadist
    1.11
     terrorist
    1.10
     jihad
    1.09
     clandestine
    1.08
     illicit
    1.08
    ihadi
    1.07
     aliases
    1.07
     gangs
    1.07
    Qaeda
    1.04
    Activations Density 1.258%

    No Known Activations