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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3971
    Prev
    Next
    INDEX
    Explanations

    phrases related to thoughts and thought processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to introspection and critical thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Bottom
    -0.63
    Availability
    -0.62
     Hi
    -0.61
     Tens
    -0.59
    ALL
    -0.59
    lain
    -0.59
     Ago
    -0.58
    adra
    -0.58
     Peninsula
    -0.58
     Mehran
    -0.58
    POSITIVE LOGITS
     provoking
    1.25
    fulness
    1.16
    fully
    1.11
    crime
    1.10
    lessly
    1.03
     processes
    0.98
     experiment
    0.94
     process
    0.92
    lessness
    0.89
    process
    0.89
    Activations Density 0.087%

    No Known Activations