© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 14737
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences and actions, especially those involving societal or political implications

    oai_token-act-pair · gpt-3.5-turbo

    references to abstract concepts or issues related to societal problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yel
    -0.68
     Spoon
    -0.66
     Pirates
    -0.63
    estern
    -0.59
     marines
    -0.57
     Sims
    -0.57
    aughed
    -0.57
     Aluminum
    -0.56
    UGH
    -0.56
     Suzuki
    -0.56
    POSITIVE LOGITS
     oneself
    0.99
    self
    0.97
     ourselves
    0.93
    selves
    0.87
    chy
    0.84
    alian
    0.84
     anew
    0.83
     yourself
    0.81
     selves
    0.80
    obe
    0.80
    Activations Density 0.215%

    No Known Activations