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

    Neuronpedia

    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. 7269
    Prev
    Next
    INDEX
    Explanations

    symbols like "Ċ" followed by sections of text that do not seem to have a clear pattern or theme

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or formatting in the text

    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
     whilst
    -1.11
     Whilst
    -0.96
     organis
    -0.92
     emphas
    -0.79
     ageing
    -0.79
     realised
    -0.77
     organising
    -0.76
    avour
    -0.74
     util
    -0.74
     scept
    -0.74
    POSITIVE LOGITS
    CLOSE
    0.98
    PHOTOS
    0.93
    SHARE
    0.87
    Newsletter
    0.85
    Lt
    0.85
    Correct
    0.83
     Legislature
    0.83
    Still
    0.82
    Officials
    0.82
    adelphia
    0.80
    Activations Density 0.601%

    No Known Activations