© 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. 20448
    Prev
    Next
    INDEX
    Explanations

    words related to future plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to planning and envisioning future scenarios

    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
     unsupported
    -0.69
     panic
    -0.69
     capit
    -0.67
     exit
    -0.65
     Brit
    -0.65
     americ
    -0.65
     whims
    -0.64
     Panic
    -0.63
     whining
    -0.62
     idiots
    -0.62
    POSITIVE LOGITS
    ued
    1.15
    ues
    1.12
    elled
    1.11
    eled
    1.11
    icked
    1.10
    aled
    1.09
    ·
    1.06
    uted
    1.05
    ved
    1.02
    ining
    1.01
    Activations Density 0.116%

    No Known Activations