© 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. 9-RES-JB
    11. 7377
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, instructions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and phrases related to requirements or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     watching
    -0.91
    watching
    -0.83
     Watching
    -0.82
    checking
    -0.82
     mindful
    -0.79
     overseeing
    -0.79
    thinking
    -0.75
     reviewing
    -0.75
    forcing
    -0.75
     debating
    -0.74
    POSITIVE LOGITS
     contain
    1.52
     undergo
    1.33
     withstand
    1.25
     belong
    1.25
     survive
    1.22
     originate
    1.22
     emit
    1.20
     conform
    1.20
     behave
    1.18
     exist
    1.16
    Activations Density 0.435%

    No Known Activations