© 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. 17077
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance and controversial events involving prominent individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to activism and media involvement

    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
     circumstance
    -0.65
    ãĤ©
    -0.60
     circumstances
    -0.59
    ãĥ£
    -0.58
    ij士
    -0.57
    ITNESS
    -0.57
    âĸ¬
    -0.57
    ãĥĭ
    -0.55
    Õ
    -0.55
    à©
    -0.54
    POSITIVE LOGITS
    paces
    1.03
    hops
    0.94
     Belfast
    0.92
     Copyright
    0.91
    hips
    0.85
     Written
    0.83
     abroad
    0.78
    "},"
    0.77
     alike
    0.77
    chool
    0.77
    Activations Density 0.389%

    No Known Activations