© 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. 9494
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of rules or restrictions being enforced or proposed

    oai_token-act-pair · gpt-3.5-turbo

    references to prohibitions or bans on various subjects

    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
     IMAGES
    -0.68
     prest
    -0.65
     rendition
    -0.64
     Maid
    -0.64
     Generations
    -0.63
     Turk
    -0.63
     Tuc
    -0.61
     Cous
    -0.61
     contrace
    -0.60
     Io
    -0.60
    POSITIVE LOGITS
    ishment
    1.43
    hammer
    1.15
    ishing
    1.13
    eful
    1.11
    lie
    0.99
    jo
    0.98
    zai
    0.95
    tering
    0.95
    nered
    0.94
    ning
    0.93
    Activations Density 0.046%

    No Known Activations