© 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. 21470
    Prev
    Next
    INDEX
    Explanations

    phrases related to police officers and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to criminal charges and incidents involving police officers

    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
    20439
    -0.74
    "—
    -0.64
    Bird
    -0.59
     HDL
    -0.59
    alions
    -0.59
    Ļ½
    -0.58
    uliffe
    -0.58
     precept
    -0.57
     thereof
    -0.57
    ospels
    -0.56
    POSITIVE LOGITS
     #
    0.99
     @
    0.94
     pic
    0.93
     eh
    0.82
     pictured
    0.81
     huh
    0.79
     (@
    0.79
     IMAGES
    0.77
     reacts
    0.76
     Photograph
    0.74
    Activations Density 0.655%

    No Known Activations