© 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. 12840
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a plan or decision to do something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intention and decision-making

    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
     UNCLASSIFIED
    -0.68
    âĢ¢âĢ¢
    -0.65
    à¼
    -0.64
     (âĪĴ
    -0.62
    reements
    -0.62
    doms
    -0.61
    phies
    -0.61
     clauses
    -0.60
     trillions
    -0.60
    20439
    -0.60
    POSITIVE LOGITS
     myself
    1.10
     somew
    0.94
     something
    0.87
     ourselves
    0.87
     ASAP
    0.80
     somet
    0.80
    romptu
    0.79
     sometime
    0.79
     someday
    0.78
     themed
    0.77
    Activations Density 0.440%

    No Known Activations