© 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. 8-RES-JB
    11. 20183
    Prev
    Next
    INDEX
    Explanations

    verbs related to planning or intention

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating planned actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.78
     Explan
    -0.68
    worthy
    -0.68
    ritical
    -0.66
    pite
    -0.65
    lights
    -0.63
    clips
    -0.62
    checking
    -0.61
     Canary
    -0.60
    guards
    -0.59
    POSITIVE LOGITS
     revise
    1.14
     pursue
    1.13
     propose
    1.10
     publish
    1.07
     introduce
    1.06
     utilize
    1.06
     continue
    1.05
     explore
    1.04
     spend
    1.04
     retire
    1.03
    Activations Density 0.111%

    No Known Activations