© 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. 11-RES-JB
    11. 18697
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical events and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dimensional
    -0.66
     listener
    -0.59
     structured
    -0.58
     enjoyment
    -0.58
     assignments
    -0.57
     prototyp
    -0.57
     homework
    -0.57
     multif
    -0.56
     hops
    -0.56
     immersion
    -0.56
    POSITIVE LOGITS
     REUTERS
    1.40
     Photograph
    1.29
     Photo
    1.24
     PHOTO
    1.14
     Picture
    1.10
     Hide
    1.08
     Image
    1.05
     Photographer
    1.00
    AFP
    0.99
     Reuters
    0.98
    Activations Density 0.224%

    No Known Activations