© 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. 24169
    Prev
    Next
    INDEX
    Explanations

    words related to advocacy, empowerment, and support in social contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to social justice and empowerment

    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
     Nope
    -0.78
    SPONSORED
    -0.64
    ITNESS
    -0.62
    Correction
    -0.61
     }}
    -0.60
    quickShipAvailable
    -0.59
    ··
    -0.57
    )\
    -0.57
    ãĤ©
    -0.56
    ))))
    -0.56
    POSITIVE LOGITS
     whilst
    1.03
     whereby
    0.92
     through
    0.87
     by
    0.84
     utilizing
    0.81
     throughout
    0.80
     and
    0.79
     via
    0.78
     enabling
    0.78
     using
    0.77
    Activations Density 1.147%

    No Known Activations