© 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. 11-RES-JB
    11. 17461
    Prev
    Next
    INDEX
    Explanations

    terms related to news and political contexts

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unexpected symbols in the text

    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
     Mous
    -0.84
     shroud
    -0.76
     ASC
    -0.75
     assemb
    -0.70
     dispers
    -0.70
     range
    -0.67
     scrambling
    -0.66
     sling
    -0.66
     museum
    -0.64
     Muller
    -0.64
    POSITIVE LOGITS
    ľ
    2.06
    Ŀ
    1.66
    ª
    1.63
    ¡
    1.60
    Ł
    1.59
    Ķ
    1.55
    «
    1.49
    ļ
    1.47
    ĸ
    1.46
    ¤
    1.45
    Activations Density 0.194%

    No Known Activations