© 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. 10082
    Prev
    Next
    INDEX
    Explanations

    actions related to planning and productivity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal development and goal-setting

    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
    iannopoulos
    -0.93
    ochet
    -0.80
     coron
    -0.79
     surn
    -0.74
     Coulter
    -0.74
     Argon
    -0.71
     taxpayers
    -0.70
     Yiannopoulos
    -0.70
     mutants
    -0.70
     imperialist
    -0.69
    POSITIVE LOGITS
     mindfulness
    1.60
     meditation
    1.47
     Meditation
    1.43
    cknow
    1.35
     willpower
    1.35
     relaxation
    1.27
     mindful
    1.24
     exercises
    1.16
     Exercise
    1.11
     habits
    1.10
    Activations Density 0.579%

    No Known Activations