© 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. 10-RES-JB
    11. 6717
    Prev
    Next
    INDEX
    Explanations

    words related to making plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating plans or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Explan
    -0.76
    quickShipAvailable
    -0.74
     assurance
    -0.72
     Warning
    -0.70
    felt
    -0.69
    heit
    -0.69
    joy
    -0.69
     Connection
    -0.64
    Sorry
    -0.63
     comprehension
    -0.63
    POSITIVE LOGITS
     pursue
    1.19
     introduce
    1.19
     capitalize
    1.17
     retire
    1.15
     unveil
    1.15
     dedicate
    1.13
     sue
    1.12
     revisit
    1.11
     intensify
    1.11
     expand
    1.10
    Activations Density 0.092%

    No Known Activations