© 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. 10-RES-JB
    11. 4714
    Prev
    Next
    INDEX
    Explanations

    words related to technology and online communication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to blogging and controversial topics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÂŃ
    -1.27
    advertisement
    -1.06
     âĢ¦"
    -1.00
    âĢ³
    -0.94
    âĢ²
    -0.89
     âĢ¦
    -0.88
     ÂŃ
    -0.88
    Advertisements
    -0.86
    âĢIJ
    -0.85
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.83
    POSITIVE LOGITS
     -
    2.60
     �
    1.48
     "-
    1.22
     --
    1.21
     ---
    1.16
    :-
    1.15
    )...
    1.08
    --
    1.06
    "...
    1.05
    ...
    1.03
    Activations Density 0.271%

    No Known Activations