© 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. 3784
    Prev
    Next
    INDEX
    Explanations

    phrases related to various social issues and challenges, such as unhealthy food, campus regulations, financial struggles, medical qualifications, nursing care, and Halloween costumes

    oai_token-act-pair · gpt-3.5-turbo

    references to social justice issues and advocacy

    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
     didnt
    -0.57
    ãĥ´
    -0.56
     USSR
    -0.55
     genesis
    -0.53
     impossibility
    -0.52
     reply
    -0.52
     proponent
    -0.51
    ³³³³³³³³
    -0.51
    REDACTED
    -0.51
     definite
    -0.51
    POSITIVE LOGITS
     anymore
    1.04
     anytime
    1.02
     amid
    0.90
     or
    0.86
     unless
    0.80
    .,"
    0.79
     lest
    0.77
     safely
    0.76
    .
    0.75
     —
    0.75
    Activations Density 0.753%

    No Known Activations