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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10102
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and personal reflection

    oai_token-act-pair · gpt-3.5-turbo

    themes related to decision-making and community consensus

    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
     charms
    -0.71
     Worm
    -0.71
     BIT
    -0.64
     Beware
    -0.63
     DATA
    -0.62
    obos
    -0.62
     Sass
    -0.62
     Reboot
    -0.61
     CLS
    -0.61
     LOVE
    -0.61
    POSITIVE LOGITS
    âĢ
    1.88
     âĢ
    1.47
    âĢij
    1.32
    áµ
    1.04
    âĢķ
    1.03
    »
    1.03
    ¨
    1.01
    âĶ
    1.01
    .�
    1.00
    ÂŃ
    0.99
    Activations Density 1.032%

    No Known Activations