© 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. 21851
    Prev
    Next
    INDEX
    Explanations

    words related to political, economic, technical, and professional aspects, as well as terms related to cosmic and surreal descriptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to themes of existentialism and identity

    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
    onen
    -0.63
    RIPT
    -0.61
    xi
    -0.57
    everal
    -0.57
    igs
    -0.56
    elfth
    -0.56
    ricanes
    -0.56
    ousands
    -0.56
    bats
    -0.55
    Chance
    -0.54
    POSITIVE LOGITS
    ized
    1.08
    istic
    1.05
    ised
    1.04
    izable
    1.03
    isable
    1.02
     insofar
    1.00
    istically
    0.93
     rather
    0.91
     whereas
    0.89
    ;
    0.87
    Activations Density 0.291%

    No Known Activations