© 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. 10224
    Prev
    Next
    INDEX
    Explanations

    first person pronouns followed by contractions and mentions of high personal involvement

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns indicating personal statements or opinions

    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
    ADVERTISEMENT
    -0.98
    colored
    -0.86
     Organizations
    -0.82
    izational
    -0.81
     totaling
    -0.81
     behaviors
    -0.81
     honors
    -0.80
    imize
    -0.78
     nonexistent
    -0.75
     unfavorable
    -0.75
    POSITIVE LOGITS
     apologise
    1.79
     realise
    1.75
     recognise
    1.75
     apologised
    1.69
     realised
    1.64
     recognised
    1.50
     learnt
    1.49
     analyse
    1.38
     criticised
    1.34
     emphas
    1.33
    Activations Density 0.264%

    No Known Activations