© 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. 17195
    Prev
    Next
    INDEX
    Explanations

    self-care related actions and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal fitness and self-care practices

    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
    calling
    -0.79
     Definitions
    -0.70
    Semitic
    -0.68
    Semitism
    -0.67
    Evil
    -0.66
     Evil
    -0.65
     surn
    -0.65
     Printed
    -0.64
     bidding
    -0.63
     Letters
    -0.62
    POSITIVE LOGITS
     conserve
    1.21
     optimize
    1.18
     accelerate
    1.16
     maximize
    1.14
     consume
    1.10
     relax
    1.10
     plateau
    1.07
     workout
    1.07
     improve
    1.06
     increase
    1.05
    Activations Density 0.379%

    No Known Activations