© 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. 9164
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing reactions or problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the consequences or effects of actions

    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
     confidently
    -0.68
    dated
    -0.68
    clusive
    -0.68
    ciples
    -0.67
     wisely
    -0.64
    finished
    -0.62
    method
    -0.62
     coached
    -0.62
    weapon
    -0.61
     enthusiastically
    -0.60
    POSITIVE LOGITS
     havoc
    1.44
     headaches
    1.43
     uproar
    1.39
     confusion
    1.22
     inconvenience
    1.22
     stir
    1.22
     disturbance
    1.22
     trouble
    1.19
     problems
    1.17
     mayhem
    1.17
    Activations Density 0.174%

    No Known Activations