© 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. 17442
    Prev
    Next
    INDEX
    Explanations

    sentences related to personal experiences and interactions with others

    oai_token-act-pair · gpt-3.5-turbo

    themes related to fear and anxiety

    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
    iosyncr
    -1.01
     redes
    -0.87
    Discuss
    -0.81
    èĢħ
    -0.81
    ãĤ©
    -0.79
    ¥ŀ
    -0.78
    erenn
    -0.76
    Detailed
    -0.75
    ocative
    -0.74
    etheless
    -0.74
    POSITIVE LOGITS
     I
    1.19
     she
    1.16
     my
    1.08
     nobody
    1.04
     they
    1.02
     SHE
    1.02
     Mom
    1.01
     Dad
    0.98
     daddy
    0.98
     Daddy
    0.96
    Activations Density 0.436%

    No Known Activations