© 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. 9-RES-JB
    11. 4740
    Prev
    Next
    INDEX
    Explanations

    legal and criminal justice-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to civic engagement and political discussions

    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
     veter
    -0.76
    CLASSIFIED
    -0.76
    ,,,,
    -0.76
    :(
    -0.72
     shenan
    -0.71
    âĢķ
    -0.69
    ,,
    -0.68
    Truth
    -0.65
    Quote
    -0.65
     tremend
    -0.64
    POSITIVE LOGITS
     apologised
    0.87
     Nato
    0.85
    ']
    0.81
     £
    0.81
     Photograph
    0.80
     recognise
    0.78
     (£
    0.77
     apologise
    0.76
     criticised
    0.76
     pictured
    0.75
    Activations Density 0.295%

    No Known Activations