© 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. 19303
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and official matters

    oai_token-act-pair · gpt-3.5-turbo

    empty or missing content

    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
     compass
    -0.87
     mushroom
    -0.85
     torpedo
    -0.81
     worm
    -0.80
     fuse
    -0.79
     reserve
    -0.79
     helic
    -0.78
     coral
    -0.76
     knockout
    -0.75
     civilisation
    -0.75
    POSITIVE LOGITS
    âĢ
    2.43
    ADVERTISEMENT
    1.92
    âĸº
    1.78
    âĸł
    1.76
    ãĢ
    1.71
    âĢł
    1.71
    âĸ
    1.70
    î
    1.65
    âĹ
    1.65
    ï
    1.64
    Activations Density 0.467%

    No Known Activations